Time Patents (Class 704/211)
  • Patent number: 11227110
    Abstract: Embodiments are disclosed for transliterating text entries across different script systems. A method according to some embodiments includes steps of: receiving an input string in a first script system input using a keyboard; segmenting, using a probabilistic model, the input string into phonemes that correspond to characters or sets of characters in a second script system; converting the phonemes in the first script system into the characters or sets of characters in the second script system, the characters or sets of characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.
    Type: Grant
    Filed: March 27, 2020
    Date of Patent: January 18, 2022
    Assignee: FACEBOOK, INC.
    Inventors: Juan Miguel Pino, Stanislav Funiak, Mridul Malpani, Gaurav Lochan
  • Patent number: 11107487
    Abstract: An apparatus and method are disclosed for processing an audio signal. The apparatus includes an input interface, a digital filterbank having an analysis part and a synthesis part, a first phase shifter, a spectral envelope adjuster, a second phase shifter, and an output interface. The first phase shifter and the second phase shifter reduce a complexity of the digital filterbank, which includes both analysis and synthesis filters that are complex-exponential modulated versions of a prototype filter.
    Type: Grant
    Filed: October 28, 2019
    Date of Patent: August 31, 2021
    Assignee: Dolby International AB
    Inventor: Per Ekstrand
  • Patent number: 11070891
    Abstract: A subtitle management system is provided that analyzes and adjusts subtitles for video content to improve the experience of viewers. Subtitles may be optimized or otherwise adjusted to display in particular regions of the video content, to display in synchronization with audio presentation of the spoken dialogue represented by the subtitles, to display in particular colors, and the like. Subtitles that are permanently integrated into the video content may be identified and addressed. These and other adjustments may be applied to address any of a variety of subtitle issues and shortcomings with conventional methods of generating subtitles.
    Type: Grant
    Filed: December 10, 2019
    Date of Patent: July 20, 2021
    Assignee: Amazon Technologies, Inc.
    Inventors: Charles Effinger, Ryan Barlow Dall, Christian Garcia Siagian, Ramakanth Mudumba, Lawrence Kyuil Chang
  • Patent number: 10997973
    Abstract: Disclosed is a voice recognition apparatus connected via a network and sharing a voice recognition function. The voice recognition apparatus includes: a microphone configured to receive a voice signal from a user's speech; a communicator configured to communicate with at least one external voice recognition apparatus; a voice recognizer configured to determine a wake-up word involved in the voice signal; and a controller configured to transmit the voice signal to the external voice recognition apparatus corresponding to the determined wake-up word. Thus, it is possible to overcome a limited voice recognition distance caused by a physical characteristic of a microphone and expand a spatial range where voice recognition is possible, thereby providing various voice recognition services to a user in more places.
    Type: Grant
    Filed: August 4, 2016
    Date of Patent: May 4, 2021
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Myoung-soon Choi, Jong-hyuk Lee
  • Patent number: 10909975
    Abstract: Systems, devices and methods are described herein for segmentation of content, and more specifically for segmentation of content in a content management system. In one aspect, a method may include receiving content associated with speech, text, or closed captioning data. The speech, the text, or the closed captioning data may be analyzed to derive at least one of a topic, subject, or event for at least a portion of the content. The content may be divided into two or more content segments based on the analyzing. At least one of the topic, the subject, or the event may be associated with at least one of the two or more content segments based on the analyzing. At least one of the two or more content segments may then be published such that each of the two or more content segments is individually accessible.
    Type: Grant
    Filed: August 31, 2018
    Date of Patent: February 2, 2021
    Assignee: Sinclair Broadcast Group, Inc.
    Inventors: Benjamin Aaron Miller, Jason D. Justman, Lora Clark Bouchard, Michael Ellery Bouchard, Kevin James Cotlove, Mathew Keith Gitchell, Stacia Lynn Haisch, Jonathan David Kersten, Matthew Karl Marchio, Peter Arthur Pulliam, George Allen Smith, Todd Christopher Tibbetts
  • Patent number: 10887075
    Abstract: A method and system implements a repeater in a link of a communication medium. The method and system enables a counter to count alternations of a clock signal received from a host or device over the link, compares a value of the counter to a reference count, adjusts a frequency selection based on the comparison of the value of the counter to the reference count, and locks the frequency selection in response to the counter matching the reference count.
    Type: Grant
    Filed: March 28, 2017
    Date of Patent: January 5, 2021
    Assignee: INTEL CORPORATION
    Inventors: Amit Kumar Srivastava, Chenchu Punnarao Bandi
  • Patent number: 10861477
    Abstract: A non-transitory computer-readable recording medium records a program for causing a computer to execute an utterance impression determination process. The utterance impression determination process includes specifying a current fundamental frequency from a voice signal which is received, calculating a relaxation value by changing the current fundamental frequency in chronological order so that the change in the current fundamental frequency becomes moderate, and evaluating the voice signal based on a degree of a magnitude of a difference between at least one feature amount associated with the current fundamental frequency and the relaxation value corresponding to the feature amount.
    Type: Grant
    Filed: September 27, 2018
    Date of Patent: December 8, 2020
    Assignee: FUJITSU LIMITED
    Inventors: Taro Togawa, Sayuri Nakayama, Takeshi Otani
  • Patent number: 10773038
    Abstract: Methods and apparatus provide acoustic detection for automated devices such as respiratory treatment apparatus. In some embodiments of the technology, acoustic analysis of noise or sound pulses, such as a cepstrum analysis, based on signals of a sound sensor (104) permits detection of obstruction (O) such as within a patient interface, mask or respiratory conduit (108) or within patient respiratory system. Some embodiments further permit detection of accessories such as an identification thereof or a condition of use thereof, such as a leak. Still further embodiments of the technology permit the detection of a patient or user who is intended to use the automated device.
    Type: Grant
    Filed: February 10, 2010
    Date of Patent: September 15, 2020
    Assignee: ResMed Pty Ltd
    Inventors: Liam Holley, Dion Charles Chewe Martin, Steven Paul Farrugia
  • Patent number: 10770079
    Abstract: An apparatus for processing an input audio signal relies on a cascade of filterbanks, the cascade having a synthesis filterbank for synthesizing an audio intermediate signal from the input audio signal, the input audio signal being represented by a plurality of first subband signals generated by an analysis filterbank, wherein a number of filterbank channels of the synthesis filterbank is smaller than a number of channels of the analysis filterbank. The apparatus furthermore has a further analysis filterbank for generating a plurality of second subband signals from the audio intermediate signal, wherein the further analysis filterbank has a number of channels being different from the number of channels of the synthesis filterbank, so that a sampling rate of a subband signal of the plurality of second subband signals is different from a sampling rate of a first subband signal of the plurality of first subband signals.
    Type: Grant
    Filed: June 22, 2018
    Date of Patent: September 8, 2020
    Assignees: Franhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V., Dolby International AB
    Inventors: Lars Villemoes, Per Ekstrand, Sascha Disch, Frederik Nagel, Stephan Wilde
  • Patent number: 10741169
    Abstract: During text-to-speech processing, a speech model creates output audio data, including speech, that corresponds to input text data that includes a representation of the speech. A spectrogram estimator estimates a frequency spectrogram of the speech; the corresponding frequency-spectrogram data is used to condition the speech model. A plurality of acoustic features corresponding to different segments of the input text data, such as phonemes, syllable-level features, and/or word-level features, may be separately encoded into context vectors; the spectrogram estimator uses these separate context vectors to create the frequency spectrogram.
    Type: Grant
    Filed: September 25, 2018
    Date of Patent: August 11, 2020
    Assignee: Amazon Technologies, Inc.
    Inventors: Jaime Lorenzo Trueba, Thomas Renaud Drugman, Viacheslav Klimkov, Srikanth Ronanki, Thomas Edward Merritt, Andrew Paul Breen, Roberto Barra-Chicote
  • Patent number: 10721509
    Abstract: A computer system constructs a decision-predictive recipient profile using sensatory data tied to an online profile of a recipient. After obtaining base sensatory data tied to the online profile of the recipient, the system may filter the base sensatory data by searching the base sensatory data for one or more machine-cognizable characteristics. The filtered sensatory data may be provided to an execution group, which may review displays of the sensatory data. Responsive to the displays of the sensatory data, the execution group may generate descriptors of the content of the filtered sensatory data and send the descriptors to the system. The system may process the descriptors to generate or augment the decision-predictive recipient profile.
    Type: Grant
    Filed: July 27, 2016
    Date of Patent: July 21, 2020
    Assignee: Accenture Global Solutions Limited
    Inventors: David Tong Nguyen, Paul Justin Mahler
  • Patent number: 10706310
    Abstract: A camera device and camera system for video-based workplace safety is provided. The camera device includes at least one imaging sensor configured to capture one or more video sequences in a workplace environment having a plurality of machines therein. The video camera further includes a processor. The processor is configured to generate a plurality of embedding vectors based on a plurality of observations. The observations include (i) a subject, (ii) an action taken by the subject, and (iii) an object on which the subject is taking the action on. The subject and object are constant. The processor is further configured to generate predictions of one or more future events based on one or more comparisons of at least some of the plurality of embedding vectors. The processor is configured to generate a signal for initiating an action to the at least one of the plurality of machines to mitigate harm.
    Type: Grant
    Filed: January 31, 2017
    Date of Patent: July 7, 2020
    Assignee: NEC Corporation
    Inventor: Bing Bai
  • Patent number: 10643028
    Abstract: Embodiments are disclosed for transliterating text entries across different script systems. A method according to some embodiments includes steps of: receiving an input string in a first script system input using a keyboard; segmenting, using a probabilistic model, the input string into phonemes that correspond to characters or sets of characters in a second script system; converting the phonemes in the first script system into the characters or sets of characters in the second script system, the characters or sets of characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.
    Type: Grant
    Filed: July 19, 2019
    Date of Patent: May 5, 2020
    Assignee: FACEBOOK, INC.
    Inventors: Juan Miguel Pino, Stanislav Funiak, Mridul Malpani, Gaurav Lochan
  • Patent number: 10643595
    Abstract: A method and apparatus of acoustic processing for a mobile device having a haptic actuator is described. A vibration drive signal for driving a haptic actuator is received. A vibration noise output from a haptic actuator is detected. At least one vibration noise metric from the detected vibration noise output and the vibration drive signal is generated. The vibration noise output level is adapted in dependence of the at least one vibration noise metric.
    Type: Grant
    Filed: March 26, 2018
    Date of Patent: May 5, 2020
    Assignee: GOODIX TECHNOLOGY (HK) COMPANY LIMITED
    Inventors: Christophe Marc Macours, Temujin Gautama, Nicolas Vincens
  • Patent number: 10636448
    Abstract: An audio processing system has a buffer, a first digital signal processing module that uses a first lookahead, a second digital signal processing module that uses a second, greater lookahead, and a cross-fader. The cross-fader fades between the output of the first digital signal processing module to the output of the second digital signal processing module, based on lookahead depth of data of the audio signal in the buffer. Other aspects are also described and claimed.
    Type: Grant
    Filed: September 17, 2018
    Date of Patent: April 28, 2020
    Assignee: APPLE INC.
    Inventor: Frank Baumgarte
  • Patent number: 10629223
    Abstract: The present invention is a system and method for increasing the playback speed of audio waves. The system analyzes an audio wave to detect a first silent section that has a length greater than a minimum short pause length required to distinguish between words. The system then calculates a new playback speed of the first silent section so that the total playback time for the first silent section is less than or equal to the minimum short pause length and controls an audio playback device to play the audio wave in a manner so that the first silent section is played back at the new playback speed. In another embodiment, the system analyzes spoken words, phonemes by phonemes, and increases the spoken word playback speed by dynamically reducing the length of each phoneme and inter-syllable silent pauses. Thus, the system functions equally well for all languages and accents.
    Type: Grant
    Filed: May 31, 2017
    Date of Patent: April 21, 2020
    Assignee: International Business Machines Corporation
    Inventor: Deepa Jain
  • Patent number: 10614829
    Abstract: One embodiment is a method of presenting an audio or audio-visual work which includes: (a) detecting media work content properties in an audio portion of the audio or audio-visual work using a media work content properties detection apparatus; (b) associating a presentation rate of the audio of the audio portion of the audio or audio-visual work with the detected media work content properties; and (c) presenting the portion of the audio or audio-visual work using the media work content properties detection apparatus so that the audio is presented at the presentation rate; wherein the media work content properties comprise one or more indicia of words of interest; and wherein the audio or audio-visual work includes conversations.
    Type: Grant
    Filed: October 7, 2015
    Date of Patent: April 7, 2020
    Assignee: Virentem Ventures, LLC
    Inventor: Donald J. Hejna, Jr.
  • Patent number: 10535365
    Abstract: According to some embodiments, an analog processing portion may receive an audio signal from a microphone. The analog processing portion may then convert the audio signal into sub-band signals and estimate an energy statistic value, such as a Signal-to-Noise Ratio (“SNR”) value, for each sub-band signal. A classification element may classify the estimated energy statistic values with analog processing such that a wakeup signal is generated when voice activity is detected. The wakeup signal may be associated with, for example, a battery-powered, always-listening audio application.
    Type: Grant
    Filed: August 27, 2018
    Date of Patent: January 14, 2020
    Inventors: Brandon David Rumberg, David W. Graham
  • Patent number: 10515618
    Abstract: A waveform data structure includes a plurality of types of frames having different data sizes. Each of the plurality of types of frames includes an auxiliary information area and a data area. The auxiliary information area includes an area for storing common effective-bit length data for a section of waveform samples, and an area for storing an identifier for identifying one of the plurality of types of frames. The data area is an area for storing extracted waveform samples which are extracted from the waveform samples based on the common effective-bit length. The number of the extracted waveform samples is determined based on the common effective-bit length.
    Type: Grant
    Filed: January 3, 2019
    Date of Patent: December 24, 2019
    Assignee: CASIO COMPUTER CO., LTD.
    Inventor: Goro Sakata
  • Patent number: 10476769
    Abstract: In accordance with an example embodiment of the present invention, disclosed is a method and an apparatus thereof for selecting a packet loss concealment procedure for a lost audio frame of a received audio signal. A method for selecting a packet loss concealment procedure comprises detecting an audio type of a received audio frame and determining a packet loss concealment procedure based on the audio type. In the method, detecting an audio type comprises determining a stability of a spectral envelope of signals of received audio frames.
    Type: Grant
    Filed: September 12, 2018
    Date of Patent: November 12, 2019
    Assignee: TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
    Inventor: Stefan Bruhn
  • Patent number: 10460739
    Abstract: A gain adjustment apparatus for use in decoding of audio that has been encoded with separate gain and shape representations includes an accuracy meter configured to estimate an accuracy measure of the shape representation, and to determine a gain correction based on the estimated accuracy measure. An envelope adjuster further included in the apparatus is configured to adjust the gain representation based on the determined gain correction.
    Type: Grant
    Filed: August 4, 2017
    Date of Patent: October 29, 2019
    Assignee: TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
    Inventors: Erik Norvell, Volodya Grancharov
  • Patent number: 10460742
    Abstract: An apparatus and method are disclosed for processing an audio signal. The apparatus includes an input interface, a digital filterbank having an analysis part and a synthesis part, a first phase shifter, a spectral envelope adjuster, a second phase shifter, and an output interface. The first phase shifter and the second phase shifter reduce a complexity of the digital filterbank, which includes both analysis and synthesis filters that are complex-exponential modulated versions of a prototype filter.
    Type: Grant
    Filed: January 22, 2018
    Date of Patent: October 29, 2019
    Assignee: Dolby International AB
    Inventor: Per Ekstrand
  • Patent number: 10453459
    Abstract: An interpreting assistant system which provides to a user captions of auditory communications in the user's vicinity. The interpreting assistant system includes a smart microphone transmitter that defines an input device which converts auditory communications into audio signals and transmit the signals a translation device, with a smart phone defining the translation device which generates a text transcript from the audio signals and send the transcript file to a display device, with the display device being defined by a wearable display interface which displays the transcript for a user to see. When in use, the interpreting assistant system provides for the display of a real time transcription and display of auditory communications such as spoken words for a user that may have hearing difficulties.
    Type: Grant
    Filed: January 31, 2018
    Date of Patent: October 22, 2019
    Inventor: Saida Ashley Florexil
  • Patent number: 10410644
    Abstract: The computational resources that are needed to apply a transform-based filterbank to a limited-bandwidth audio signals are reduced by performing an integrated process of combining real-valued input data into complex-valued data and applying a short transform to the complex-valued data, applying a bank of very short transforms to the output of the integrated process, and deriving a sequence of real-valued output data from the outputs of the bank of very short transforms.
    Type: Grant
    Filed: March 19, 2012
    Date of Patent: September 10, 2019
    Assignee: Dolby Laboratories Licensing Corporation
    Inventor: Matthew C. Fellers
  • Patent number: 10402651
    Abstract: A system for exploiting visual information for enhancing audio signals via source separation and beamforming is disclosed. The system may obtain visual content associated with an environment of a user, and may extract, from the visual content, metadata associated with the environment. The system may determine a location of the user based on the extracted metadata. Additionally, the system may load, based on the location, an audio profile corresponding to the location of the user. The system may also load a user profile of the user that includes audio data associated with the user. Furthermore, the system may cancel, based on the audio profile and user profile, noise from the environment of the user. Moreover, the system may include adjusting, based on the audio profile and user profile, an audio signal generated by the user so as to enhance the audio signal during a communications session of the user.
    Type: Grant
    Filed: February 26, 2018
    Date of Patent: September 3, 2019
    Assignee: AT&T Intellectual Property I, L.P.
    Inventors: Dimitrios Dimitriadis, Donald J. Bowen, Lusheng Ji, Horst J. Schroeter
  • Patent number: 10402489
    Abstract: Embodiments are disclosed for transliterating text entries across different script systems. A method according to some embodiments includes steps of: receiving an input string in a first script system input using a keyboard; segmenting, using a probabilistic model, the input string into phonemes that correspond to characters or sets of characters in a second script system; converting the phonemes in the first script system into the characters or sets of characters in the second script system, the characters or sets of characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.
    Type: Grant
    Filed: December 21, 2016
    Date of Patent: September 3, 2019
    Assignee: FACEBOOK, INC.
    Inventors: Juan Miguel Pino, Stanislav Funiak, Mridul Malpani, Gaurav Lochan
  • Patent number: 10305831
    Abstract: This disclosure describes systems, methods, and apparatus for precluding transmission of messages that breach one or more compliance or legal framework. In particular, messages, whether digital, written, or verbal, can be stopped from leaving a device on which they are created, thereby preventing non-compliant messages from reaching intermediary servers that could constitute a compliance violation even if the message never reached a recipient.
    Type: Grant
    Filed: December 16, 2014
    Date of Patent: May 28, 2019
    Assignee: FairWords, Inc.
    Inventors: Anish Parikh, Evan M. Caron, Vadim Polosatov
  • Patent number: 10290307
    Abstract: Captured vocals may be automatically transformed using advanced digital signal processing techniques that provide captivating applications, and even purpose-built devices, in which mere novice user-musicians may generate, audibly render and share musical performances. In some cases, the automated transformations allow spoken vocals to be segmented, arranged, temporally aligned with a target rhythm, meter or accompanying backing tracks and pitch corrected in accord with a score or note sequence. Speech-to-song music applications are one such example. In some cases, spoken vocals may be transformed in accord with musical genres such as rap using automated segmentation and temporal alignment techniques, often without pitch correction. Such applications, which may employ different signal processing and different automated transformations, may nonetheless be understood as speech-to-rap variations on the theme.
    Type: Grant
    Filed: May 26, 2017
    Date of Patent: May 14, 2019
    Assignee: SMULE, INC.
    Inventors: Parag Chordia, Mark Godfrey, Alexander Rae, Prerna Gupta, Perry R. Cook
  • Patent number: 10291966
    Abstract: A method includes receiving, at a content server from a media device, a request for media content at a first playback rate. The media content is available to the content server at a second playback rate that is different from the first playback rate. The method includes generating modified media content by modifying a first portion of the media content to have a second format corresponding to a third media playback rate. The first portion having a first media characteristic. The third playback rate is different than the first playback rate and is different than the second playback rate. The third playback rate is selected such that the modified media content has a third format corresponding to the first playback rate. The method further includes sending the modified media content from the content server to a media device.
    Type: Grant
    Filed: March 23, 2017
    Date of Patent: May 14, 2019
    Assignee: AT&T INTELLECTUAL PROPERTY I, L.P.
    Inventors: Andrej Ljolje, Ann Syrdal, Alistair Conkie
  • Patent number: 10129671
    Abstract: Hearing device configuration and hearing treatment using categorical perception; systems and methods for categorical perception based configuration of hearing devices and hearing treatment.
    Type: Grant
    Filed: February 24, 2014
    Date of Patent: November 13, 2018
    Assignee: Securboration, Inc.
    Inventors: Lee Krause, Rahul Shrivastav
  • Patent number: 10115402
    Abstract: An audio packet error concealment system includes an encoding unit for encoding an audio signal consisting of a plurality of frames, and an auxiliary information encoding unit for estimating and encoding auxiliary information about a temporal change of power of the audio signal. The auxiliary information is used in packet loss concealment in decoding of the audio signal. The auxiliary information about the temporal change of power may contain a parameter that functionally approximates a plurality of powers of subframes shorter than one frame, or may contain information about a vector obtained by vector quantization of a plurality of powers of subframes shorter than one frame.
    Type: Grant
    Filed: October 20, 2016
    Date of Patent: October 30, 2018
    Assignee: NTT DOCOMO, INC.
    Inventors: Kimitaka Tsutsumi, Kei Kikuiri
  • Patent number: 10115399
    Abstract: The disclosure relates to an audio classifier comprising: a first processor having hard-wired logic configured to receive an audio signal and detect audio activity from the audio signal; and a second processor having reconfigurable logic configured to classify the audio signal as a type of audio signal in response to the first processor detecting audio activity.
    Type: Grant
    Filed: July 20, 2016
    Date of Patent: October 30, 2018
    Assignee: NXP B.V.
    Inventors: Ludovick Dominique Joel Lepauloux, Laurent Le Faucheur
  • Patent number: 10103958
    Abstract: In accordance with an example embodiment of the present invention, disclosed is a method and an apparatus thereof for selecting a packet loss concealment procedure for a lost audio frame of a received audio signal. A method for selecting a packet loss concealment procedure comprises detecting an audio type of a received audio frame and determining a packet loss concealment procedure based on the audio type. In the method, detecting an audio type comprises determining a stability of a spectral envelope of signals of received audio frames.
    Type: Grant
    Filed: June 21, 2017
    Date of Patent: October 16, 2018
    Assignee: TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
    Inventor: Stefan Bruhn
  • Patent number: 10098146
    Abstract: A processor is disclosed. The processor includes a first-receiver-node for receiving a first-receiver-signal, a second-receiver-node for receiving a second-receiver-signal, a first-output-node for coupling to a digital-baseband-processor, a second-output-node for coupling to the digital-baseband-processor and a first-active-data-pipe extending between the first-receiver-node and the first-output-node. The first-active-data-pipe includes a first-analog-to-digital-converter comprising a first-ADC-input coupled to the first-receiver-node and a first-ADC-output coupled to the first-output-node. The first-analog-to-digital-converter is configured to provide a first-digital-signal to the first-output-node. The processor comprises a first-reference-node and a configurable-data-pipe extending between the second-receiver-node and the second-output-node.
    Type: Grant
    Filed: November 18, 2016
    Date of Patent: October 9, 2018
    Assignee: NXP B.V.
    Inventors: Jan Niehof, Shagun Bajoria, Muhammed Bolatkale, Robert Rutten, Lucien Johannes Breems, Johannes Hubertus Antonius Brekelmans
  • Patent number: 10032458
    Abstract: An apparatus for processing an input audio signal relies on a cascade of filterbanks, the cascade having a synthesis filterbank for synthesizing an audio intermediate signal from the input audio signal, the input audio signal being represented by a plurality of first subband signals generated by an analysis filterbank, wherein a number of filterbank channels of the synthesis filterbank is smaller than a number of channels of the analysis filterbank. The apparatus furthermore has a further analysis filterbank for generating a plurality of second subband signals from the audio intermediate signal, wherein the further analysis filterbank has a number of channels being different from the number of channels of the synthesis filterbank, so that a sampling rate of a subband signal of the plurality of second subband signals is different from a sampling rate of a first subband signal of the plurality of first subband signals.
    Type: Grant
    Filed: March 15, 2017
    Date of Patent: July 24, 2018
    Assignees: Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V., Dolby International AB
    Inventors: Lars Villemoes, Per Ekstrand, Sascha Disch, Frederik Nagel, Stephan Wilde
  • Patent number: 10014003
    Abstract: A method of detecting a particular abnormal sound in an environment with background noise is provided. The method includes acquiring a sound from a microphone, separating abnormal sounds from the input sound based on non-negative matrix factorization (NMF), extracting Mel-frequency cepstral coefficient (MFCC) parameters according to the separated abnormal sounds, calculating hidden Markov model (HMM) likelihoods according to the separated abnormal sounds, and comparing the likelihoods of the separated abnormal sounds with a reference value to determine whether or not an abnormal sound has occurred. According to the method, based on NMF, a sound to be detected is compared with ambient noise in a one-to-one basis and classified so that the sound may be stably detected even in an actual environment with multiple noises.
    Type: Grant
    Filed: February 11, 2016
    Date of Patent: July 3, 2018
    Assignee: Gwangju Institute of Science and Technology
    Inventors: Hong-Kook Kim, Dong Yun Lee, Kwang Myung Jeon
  • Patent number: 9992321
    Abstract: A mobile terminal with a built-in voice message searching function includes: a voice recording module configured to record a voice searching signal from a user and to send the voice searching signal to the pre-processing module for pre-processing, a pre-processing module configured to pre-process the voice searching signal, and to send the pre-processed signal to the matching module for signal matching, a matching module configured to extract a characteristic parameter of the pre-processed signal, to calculate a similarity of the extracted characteristic parameter with a characteristic parameter of a stored voice message, and to send the voice message with a similarity higher than or equal to a threshold to the result outputting module, and a result outputting module configured to display the voice message with the similarity higher than or equal to the threshold on a screen of the mobile terminal.
    Type: Grant
    Filed: July 9, 2013
    Date of Patent: June 5, 2018
    Assignee: ZTE CORPORATION
    Inventor: Zheng Dang
  • Patent number: 9990917
    Abstract: A system, article, and method of random access compression of transducer data for automatic speech recognition decoding.
    Type: Grant
    Filed: April 13, 2015
    Date of Patent: June 5, 2018
    Assignee: Intel Corporation
    Inventor: Joachim Hofer
  • Patent number: 9978065
    Abstract: Embodiments of the invention are directed to systems and methods for voice filtering. In some embodiments, an original voice segment from a user may be received. The received original voice segment may be modified using a first predetermined algorithm. The modified voice segment may be sent to an authentication server. At the authentication server, the modified voice segment may be reconstructed into the original voice segment using a second predetermined algorithm. The user may be authenticated for a transaction based at least in part on the reconstructed original voice segment.
    Type: Grant
    Filed: June 25, 2014
    Date of Patent: May 22, 2018
    Assignee: Visa International Service Association
    Inventors: Shaw Li, Dhiraj Sharda, Douglas Fisher
  • Patent number: 9972294
    Abstract: Multiple audio files may be synchronized using harmonic sound included in audio content obtained from audio tracks. Individual audio tracks are partitioned into multiple temporal windows of a first and second temporal window length. Individual audio waveforms for individual temporal windows of the first and second window length are transformed into frequency space in which energy is represented as a function of frequency. Individual pitches and magnitudes of harmonic sound determined for individual temporal windows may be compared using a multi-resolution framework to correlate pitches and harmonic energy of multiple audio tracks to one another.
    Type: Grant
    Filed: March 14, 2017
    Date of Patent: May 15, 2018
    Assignee: GoPro, Inc.
    Inventor: David Tcheng
  • Patent number: 9940943
    Abstract: A method for resampling an audio-frequency signal with an output sampling frequency, for a current signal frame. The method is used when the preceding frame is sampled at a first sampling frequency which is different from a second sampling frequency of the current frame. The method includes: determining a first and second segments of the signal by adding samples at zero at the end of stored samples of the preceding frame and at the start of samples of the current frame, respectively; obtaining the first resampled segment and the second resampled segment by applying at least one resampling filter respectively to the first segment resampling the first frequency at the output frequency, and to the second segment resampling the second frequency at the output frequency; and combining the overlapping portion of the first and second resampled segments to obtain at least one portion of the resampled current frame.
    Type: Grant
    Filed: December 11, 2014
    Date of Patent: April 10, 2018
    Assignee: ORANGE
    Inventors: Stephane Ragot, Jerome Daniel, Balazs Kovesi
  • Patent number: 9904851
    Abstract: A system for exploiting visual information for enhancing audio signals via source separation and beamforming is disclosed. The system may obtain visual content associated with an environment of a user, and may extract, from the visual content, metadata associated with the environment. The system may determine a location of the user based on the extracted metadata. Additionally, the system may load, based on the location, an audio profile corresponding to the location of the user. The system may also load a user profile of the user that includes audio data associated with the user. Furthermore, the system may cancel, based on the audio profile and user profile, noise from the environment of the user. Moreover, the system may include adjusting, based on the audio profile and user profile, an audio signal generated by the user so as to enhance the audio signal during a communications session of the user.
    Type: Grant
    Filed: June 11, 2014
    Date of Patent: February 27, 2018
    Assignee: AT&T INTELLECTUAL PROPERTY I, L.P.
    Inventors: Dimitrios Dimitriadis, Donald J. Bowen, Lusheng Ji, Horst J. Schroeter
  • Patent number: 9877066
    Abstract: This method for synchronizing a first multimedia stream rendered on a first terminal and a second multimedia stream rendered on a second terminal, comprises a step of generation, from an original audio sequence of the first stream, of original audio fingerprints, and further comprises steps of: a) generation from a first sequence of the first stream first audio fingerprints; b) comparison between the first fingerprints and the original fingerprints in order to obtain one or more first synchronization positions; c) correlation of the first sequence with one or more pieces of the original sequence located around the first synchronization positions in order to obtain a second synchronization position; d) rendering of the second stream on the second terminal using the second synchronization position.
    Type: Grant
    Filed: April 2, 2013
    Date of Patent: January 23, 2018
    Assignee: THOMSON LICENSING DTV
    Inventors: Quang Khanh Ngoc Duong, Yvon Legallais, Christopher Howson
  • Patent number: 9870777
    Abstract: Methods are disclosed for an encoder to embed a data stream into a quantized PCM digital audio signal and for a corresponding decoder to both retrieve the data stream and losslessly reconstruct the exact original audio. Some methods employ complimentary amplification and attenuation, while others employ gain redistribution. Pre-emphasis and soft clipping techniques are described as methods of losslessly reducing the peak excursion of the PCM audio signal. Also described is the lossless placing of data at predetermined positions within an audio stream.
    Type: Grant
    Filed: October 24, 2012
    Date of Patent: January 16, 2018
    Inventors: Peter Graham Craven, Malcolm Law
  • Patent number: 9858941
    Abstract: A method includes determining, at an encoder, phase adjustment parameters based on a high-band residual signal. The method also includes inserting the phase adjustment parameters into an encoded version of the audio signal to enable phase adjustment during reconstruction of the audio signal from the encoded version of the audio signal.
    Type: Grant
    Filed: November 21, 2014
    Date of Patent: January 2, 2018
    Assignee: QUALCOMM Incorporated
    Inventors: Venkatraman S. Atti, Venkata Subrahmanyam Chandra Sekhar Chebiyyam
  • Patent number: 9858039
    Abstract: A method, system, and computer program product for human interface design. Embodiments proceed upon receiving a markup language description of user interface pages (e.g., HTML pages), then, without modifying the user interface page, parsing the markup language description to identify user interface objects configured to perform an operation responsive to a keyboard or mouse or pointing device. One or more mapping techniques serve to relate the parsed-out operation(s) to one or more voice commands. In some embodiments, the parser recognizes interface objects in forms such as a button, a textbox, a checkbox, or an option menu, and the voice commands correspond to an aspect that is displayed when rendering the interface object (e.g., a button label, a menu option, etc.). After receiving a user utterance, the utterance is converted into a text representation which in turn is mapped to voice commands that were parsed from the user interface page.
    Type: Grant
    Filed: January 28, 2014
    Date of Patent: January 2, 2018
    Assignee: Oracle International Corporation
    Inventors: Saurabh Kumar, Srinivasa Rao Kowdeed, Kavin Kumar Kuppusamy
  • Patent number: 9799344
    Abstract: An audio signal processing device comprises a discontinuity detector configured to determine an occurrence of a discontinuity from a sudden increase of an amplitude of decoded audio obtained by decoding the first audio packet which is received correctly after an occurrence of a packet loss, and a discontinuity corrector for correcting the discontinuity of the decoded audio.
    Type: Grant
    Filed: April 28, 2016
    Date of Patent: October 24, 2017
    Assignee: NTT DoCoMo, Inc.
    Inventors: Kimitaka Tsutsumi, Kei Kikuiri, Atsushi Yamaguchi
  • Patent number: 9792915
    Abstract: An apparatus for processing an input audio signal relies on a cascade of filterbanks, the cascade having a synthesis filterbank for synthesizing an audio intermediate signal from the input audio signal, the input audio signal being represented by a plurality of first subband signals generated by an analysis filterbank, wherein a number of filterbank channels of the synthesis filterbank is smaller than a number of channels of the analysis filterbank. The apparatus furthermore has a further analysis filterbank for generating a plurality of second subband signals from the audio intermediate signal, wherein the further analysis filterbank has a number of channels being different from the number of channels of the synthesis filterbank, so that a sampling rate of a subband signal of the plurality of second subband signals is different from a sampling rate of a first subband signal of the plurality of first subband signals.
    Type: Grant
    Filed: September 5, 2012
    Date of Patent: October 17, 2017
    Assignees: Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V., Dolby International AB
    Inventors: Lars Villemoes, Per Ekstrand, Sascha Disch, Frederik Nagel, Stephan Wilde
  • Patent number: 9712414
    Abstract: In accordance with an example embodiment of the present invention, disclosed is a method and an apparatus thereof for selecting a packet loss concealment procedure for a lost audio frame of a received audio signal. A method for selecting a packet loss concealment procedure comprises detecting an audio type of a received audio frame and determining a packet loss concealment procedure based on the audio type. In the method, detecting an audio type comprises determining a stability of a spectral envelope of signals of received audio frames.
    Type: Grant
    Filed: May 12, 2015
    Date of Patent: July 18, 2017
    Assignee: TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
    Inventor: Stefan Bruhn
  • Patent number: 9640159
    Abstract: Multiple audio files may be synchronized using harmonic sound included in audio content obtained from audio tracks. Individual audio tracks are partitioned into multiple temporal windows of a first and second temporal window length. Individual audio waveforms for individual temporal windows of the first and second window length are transformed into frequency space in which energy is represented as a function of frequency. Individual pitches and magnitudes of harmonic sound determined for individual temporal windows may be compared using a multi-resolution framework to correlate pitches and harmonic energy of multiple audio tracks to one another.
    Type: Grant
    Filed: August 25, 2016
    Date of Patent: May 2, 2017
    Assignee: GoPro, Inc.
    Inventor: David Tcheng