Patents Examined by Daniel Abebe
  • Patent number: 9836529
    Abstract: A system for performing semantic search receives an electronic text corpus and separates the text corpus into a plurality of sentences. The system parses and converts each sentence into a sentence tree. The system receives a search query and matches the search query with one or more of the sentence trees.
    Type: Grant
    Filed: March 10, 2015
    Date of Patent: December 5, 2017
    Assignee: ORACLE INTERNATIONAL CORPORATION
    Inventors: Vladimir Zelevinsky, Yevgeniy Dashevsky, Diana Ye
  • Patent number: 9837090
    Abstract: An apparatus and method for encoding and decoding a signal for high frequency bandwidth extension are provided. An encoding apparatus may down-sample a time domain input signal, may core-encode the down-sampled time domain input signal, may transform the core-encoded time domain input signal to a frequency domain input signal, and may perform bandwidth extension encoding using a basic signal of the frequency domain input signal.
    Type: Grant
    Filed: November 6, 2015
    Date of Patent: December 5, 2017
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Ki Hyun Choo, Eun Mi Oh, Ho Sang Sung
  • Patent number: 9830913
    Abstract: A microphone assembly includes an acoustic sensor and a voice activity detector on an integrated circuit coupled to an external-device interface. The acoustic sensor produces an electrical signal representative of acoustic energy detected by the sensor. A filter bank separates data representative of the acoustic energy into a plurality of frequency bands. A power tracker obtains a power estimate for at least one band, including a first estimate based on relatively fast changes in a power metric of the data and a second estimate based on relatively slow changes in a power metric of the data. The presence of voice activity in the electrical signal is based upon the power estimate.
    Type: Grant
    Filed: September 22, 2015
    Date of Patent: November 28, 2017
    Assignee: Knowles Electronics, LLC
    Inventors: Henrik Thomsen, Dibyendu Nandy
  • Patent number: 9830923
    Abstract: In some embodiments, a pitch filter for filtering a preliminary audio signal generated from an audio bitstream is disclosed. The pitch filter has an operating mode selected from one of either: (i) an active mode where the preliminary audio signal is filtered using filtering information to obtain a filtered audio signal, and (ii) an inactive mode where the pitch filter is disabled. The preliminary audio signal is generated in an audio encoder or audio decoder having a coding mode selected from at least two distinct coding modes, and the pitch filter is capable of being selectively operated in either the active mode or the inactive mode while operating in the coding mode based on control information.
    Type: Grant
    Filed: November 20, 2015
    Date of Patent: November 28, 2017
    Assignee: Dolby International AB
    Inventors: Barbara Resch, Kristofer Kjörling, Lars Villemoes
  • Patent number: 9824685
    Abstract: A handsfree device, which is coupled to a data processing device, may be operable to monitor at least one audio stream for occurrence of at least one keyword. Upon recognition of the at least one keyword, the handsfree device may establish a first connection between the handsfree device and the data processing device for launching a voice interface in the data processing device. The handsfree device may send audio data received after the recognition of the at least one keyword to the data processing device, via the first connection for responding to the audio data via the voice interface. During a keyword configuration operation, the handsfree device may send at least one inputted keyword to the data processing device for recording. The handsfree device may receive, via a second connection, the recorded at least one keyword from the data processing device for keyword configuration of the handsfree device.
    Type: Grant
    Filed: November 13, 2015
    Date of Patent: November 21, 2017
    Assignee: Google Inc.
    Inventor: John Richard Stracke, Jr.
  • Patent number: 9818429
    Abstract: A method and apparatus to encoding or decoding an audio signal is provided. In the method and apparatus, a noise-floor level to use in encoding or decoding a high frequency signal is updated according to the degree of a voiced or unvoiced sound included in the signal.
    Type: Grant
    Filed: October 9, 2015
    Date of Patent: November 14, 2017
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Ki-hyun Choo, Eun-mi Oh, Ho-sang Sung, Jung-Hoe Kim, Mi-young Kim
  • Patent number: 9812109
    Abstract: System, apparatus and method for determining semantic information from audio, where incoming audio is sampled and processed to extract audio features, including temporal, spectral, harmonic and rhythmic features. The extracted audio features are compared to stored audio templates that include ranges and/or values for certain features and are tagged for specific ranges and/or values. Extracted audio features that are most similar to one or more templates from the comparison are identified according to the tagged information. The tags are used to determine the semantic audio data that includes genre, instrumentation, style, acoustical dynamics, and emotive descriptor for the audio signal.
    Type: Grant
    Filed: October 16, 2015
    Date of Patent: November 7, 2017
    Assignee: THE NIELSEN COMPANY (US), LLC
    Inventors: Alan Neuhauser, John Stavropoulos
  • Patent number: 9799333
    Abstract: A system and method are provided for performing speech processing. A system includes an audio detection system configured to receive a signal including speech and a memory having stored therein a database of keyword models forming an ensemble of filters associated with each keyword in the database. A processor is configured to receive the signal including speech from the audio detection system, decompose the signal including speech into a sparse set of phonetic impulses, and access the database of keywords and convolve the sparse set of phonetic impulses with the ensemble of filters. The processor is further configured to identify keywords within the signal including speech based a result of the convolution and control operation the electronic system based on the keywords identified.
    Type: Grant
    Filed: August 31, 2015
    Date of Patent: October 24, 2017
    Assignee: The Johns Hopkins University
    Inventors: Keith Kintzley, Aren Jansen, Hynek Hermansky, Kenneth Church
  • Patent number: 9792918
    Abstract: Provided are an audio encoding method and apparatus and an audio decoding method and apparatus in which audio signals can be encoded or decoded so that sound images can be localized at any desired position for each object audio signal. The audio decoding method generating a third downmix signal by combining a first downmix signal extracted from a first audio signal and a second downmix signal extracted from a second audio signal; generating third object-based side information by combining first object-based side information extracted from the first audio signal and second object-based side information extracted from the second audio signal; converting the third object-based side information into channel-based side information; and generating a multi-channel audio signal using the third downmix signal and the channel-based side information.
    Type: Grant
    Filed: July 1, 2016
    Date of Patent: October 17, 2017
    Assignee: LG Electronics Inc.
    Inventors: Dong Soo Kim, Hee Suk Pang, Jae Hyun Lim, Sung Yong Yoon, Hyun Kook Lee
  • Patent number: 9792894
    Abstract: According to an embodiment, a speech synthesis dictionary creating device includes a first speech input unit, a second speech input unit, a determining unit, and a creating unit. The first speech input unit receives input of first speech data. The second speech input unit receives input of second speech data which is considered to be appropriate speech data. The determining unit determines whether or not a speaker of the first speech data is the same as a speaker of the second speech data. When the determining unit determines that the speaker of the first speech data is the same as the speaker of the second speech data, the creating unit creates a speech synthesis dictionary using the first speech data and using a text corresponding to the first speech data.
    Type: Grant
    Filed: December 16, 2015
    Date of Patent: October 17, 2017
    Assignee: KABUSHIKI KAISHA TOSHIBA
    Inventors: Kentaro Tachibana, Masahiro Morita, Takehiko Kagoshima
  • Patent number: 9779736
    Abstract: Systems and methods are presented for efficient cross-fading (or other multiple clip processing) of compressed domain information streams on a user or client device, such as a telephone, tablet, computer or MP3 player, or any consumer device with audio playback. Exemplary implementation systems may provide cross-fade between AAC/Enhanced AAC Plus (EAACPIus) information streams or between MP3 information streams or even between information streams of unmatched formats (e.g. AAC to MP3 or MP3 to AAC). Furthermore, these systems are distinguished by the fact that cross-fade is directly applied to the compressed bitstreams so that a single decode operation may be performed on the resulting bitstream. Moreover, using the described methods, similar cross fade in the compressed domain between information streams utilizing other formats of compression, such as, for example, MP2, AC-3, PAC, etc. can also be advantageously implemented.
    Type: Grant
    Filed: April 17, 2013
    Date of Patent: October 3, 2017
    Assignee: Sirius XM Radio Inc.
    Inventors: Raymond Lowe, Mark Kalman, Deepen Sinha, Christopher Ward
  • Patent number: 9767802
    Abstract: IP telephony communications are conducted by sending both audio data produced by a CODEC that represents received spoken audio input, and a textual representation of the spoken audio input. A receiving device utilizes the textual representation of the spoken audio input to help recreate the spoken audio input when a portion of the CODEC data is missing. The textual representation can be generated by a speech-to-text function. Alternatively, the textual representation can be a notation of extracted phonemes.
    Type: Grant
    Filed: December 15, 2014
    Date of Patent: September 19, 2017
    Assignee: VONAGE BUSINESS INC.
    Inventor: Itay Bianco
  • Patent number: 9754569
    Abstract: System, apparatus and method for determining semantic information from audio, where incoming audio is sampled and processed to extract audio features, including temporal, spectral, harmonic and rhythmic features. The extracted audio features are compared to stored audio templates that include ranges and/or values for certain features and are tagged for specific ranges and/or values. The semantic information may be associated with audio signature data Extracted audio features that are most similar to one or more templates from the comparison are identified according to the tagged information. The tags are used to determine the semantic audio data that includes genre, instrumentation, style, acoustical dynamics, and emotive descriptor for the audio signal.
    Type: Grant
    Filed: October 7, 2015
    Date of Patent: September 5, 2017
    Assignee: THE NIELSEN COMPANY (US), LLC
    Inventors: Alan Neuhauser, John Stavropoulos
  • Patent number: 9747918
    Abstract: Systems and methods for adjusting pitch of an audio signal include detecting input notes in the audio signal, mapping the input notes to corresponding output notes, each output note having an associated upper note boundary and lower note boundary, and modifying at least one of the upper note boundary and the lower note boundary of at least one output note in response to previously received input notes. Pitch of the input notes may be shifted to match an associated pitch of corresponding output notes. Delay of the pitch shifting process may be dynamically adjusted based on detected stability of the input notes.
    Type: Grant
    Filed: August 6, 2015
    Date of Patent: August 29, 2017
    Assignee: Harman International Industries, Incorporated
    Inventors: Peter R. Lupini, Glen A. Rutledge, Norm Campbell
  • Patent number: 9747902
    Abstract: A system for use in assisting a user in a social interaction with another person is provided, the system being configured to determine whether the user recognizes the person and, if it is determined that the user does not recognize the person, to provide information to the user about the person. A corresponding method and computer program product for performing the method are also provided.
    Type: Grant
    Filed: June 1, 2012
    Date of Patent: August 29, 2017
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Radu Serban Jasinschi, Murtaza Bulut, Luca Bellodi
  • Patent number: 9747284
    Abstract: A method for machine translation, comprising receiving a source string in a source language, an indication of a target language, and user identification information. The method includes using the user identification information to identify at least one memory with user-specific translation data. The method includes tokenizing the source string, using at least one processor, to produce a tokenized source string comprising any unique temporary textual elements associated with corresponding target textual elements during tokenization. The method includes obtaining a translated string from a translator, the translated string being at least a partial translation of the tokenized source string and including all of the unique temporary textual elements. The method includes generating an output string using at least one processor, the generation comprising replacing all of the unique temporary textual elements in the translated string with the associated target textual elements.
    Type: Grant
    Filed: August 26, 2015
    Date of Patent: August 29, 2017
    Inventors: James Peter Marciano, Dean S. Blodgett
  • Patent number: 9741357
    Abstract: System and method embodiments are provided for very short pitch detection and coding for speech or audio signals. The system and method include detecting whether there is a very short pitch lag in a speech or audio signal that is shorter than a conventional minimum pitch limitation using a combination of time domain and frequency domain pitch detection techniques. The pitch detection techniques include using pitch correlations in time domain and detecting a lack of low frequency energy in the speech or audio signal in frequency domain. The detected very short pitch lag is coded using a pitch range from a predetermined minimum very short pitch limitation that is smaller than the conventional minimum pitch limitation.
    Type: Grant
    Filed: June 19, 2015
    Date of Patent: August 22, 2017
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Yang Gao, Fengyan Qi
  • Patent number: 9740680
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing numeric representations of words. One of the methods includes obtaining a set of training data, wherein the set of training data comprises sequences of words; training a classifier and an embedding function on the set of training data, wherein training the embedding function comprises obtained trained values of the embedding function parameters; processing each word in the vocabulary using the embedding function in accordance with the trained values of the embedding function parameters to generate a respective numerical representation of each word in the vocabulary in the high-dimensional space; and associating each word in the vocabulary with the respective numeric representation of the word in the high-dimensional space.
    Type: Grant
    Filed: May 18, 2015
    Date of Patent: August 22, 2017
    Assignee: Google Inc.
    Inventors: Tomas Mikolov, Kai Chen, Gregory S. Corrado, Jeffrey A. Dean
  • Patent number: 9734824
    Abstract: A system and method for applying a convolutional neural network (CNN) to speech recognition. The CNN may provide input to a hidden Markov model and has at least one pair of a convolution layer and a pooling layer. The CNN operates along the frequency axis. The CNN has units that operate upon one or more local frequency bands of an acoustic signal. The CNN mitigates acoustic variation.
    Type: Grant
    Filed: May 25, 2015
    Date of Patent: August 15, 2017
    Assignees: THE GOVERNING COUNCIL OF THE UNIVERSITY OF TORONTO
    Inventors: Gerald Bradley Penn, Hui Jiang, Ossama Abdelhamid Mohamed Abdelhamid, Abdel-rahman Samir Abdel-rahman Mohamed
  • Patent number: 9728195
    Abstract: Present disclosure provide a linear prediction-based noise signal processing method includes: acquiring a noise signal, and obtaining a linear prediction coefficient according to the noise signal; filtering the noise signal according to the linear prediction coefficient, to obtain a linear prediction residual signal; obtaining a spectral envelope of the linear prediction residual signal according to the linear prediction residual signal; and encoding the spectral envelope of the linear prediction residual signal. According to the noise processing method, the noise generation method, the encoder, the decoder, and the encoding and decoding system that are in the embodiments of the present disclosure, more spectral details of an original background noise signal can be recovered, so that comfort noise can be closer to original background noise in terms of subjective auditory perception of a user, and subjective perception quality of the user is improved.
    Type: Grant
    Filed: September 29, 2016
    Date of Patent: August 8, 2017
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventor: Zhe Wang