Patents Examined by James S. Wozniak
  • Patent number: 10489516
    Abstract: A speech recognition terminal includes: a voice input unit to accept an input of a voice; a speech recognition command unit to command a speech recognition unit to convert voices of joined voice data acquired by the voice input unit joining the voice data of the voice accepted by the voice input unit to the voice data of the voice accepted previously into character information of a first language at an interval of predetermined time; a translation command unit to command a translation unit to translate first character information of a first language into a second language whenever receiving the first character information of the first language converted by the voice recognition unit; and a display unit to display the first character information of the second language translated by the translation unit together with the first character information of the first language.
    Type: Grant
    Filed: March 29, 2017
    Date of Patent: November 26, 2019
    Assignee: Fujitsu Social Science Laboratory Limited
    Inventor: Toshikazu Fukuoka
  • Patent number: 10482874
    Abstract: Systems and processes for operating a digital assistant using a hierarchical belief state are disclosed. In an example process, a user utterance of a dialog is received. A belief state for the dialog is determined. The belief state comprises a plurality of dialog slots. Each dialog slot of the plurality of dialog slots includes a respective marginal certainty for a concept or property represented by the respective dialog slot. A first dialog slot of the plurality of dialog slots further includes one or more joint certainties for one or more interpretations arising from the first dialog slot. Based on the marginal certainty of each dialog slot of the plurality of dialog slots and the one or more joint certainties of the first dialog slot, a policy action is selected from a plurality of candidate policy actions that correspond to the belief state. The selected policy action is performed.
    Type: Grant
    Filed: August 15, 2017
    Date of Patent: November 19, 2019
    Assignee: Apple Inc.
    Inventors: Blaise Thomson, Anders Johannsen, Diarmuid Ó Séaghdha, Federico Flego, Luca Simonelli, Stephen J. Young, Thomas David Voice, Thorvaldur Pall Helgason
  • Patent number: 10475471
    Abstract: In accordance with embodiments of the present disclosure, an integrated circuit for implementing at least a portion of an audio device may include an audio output configured to reproduce audio information by generating an audio output signal for communication to at least one transducer of the audio device, a microphone input configured to receive an input signal indicative of ambient sound external to the audio device, and a processor configured to implement an impulsive noise detector. The impulsive noise detector may comprise a plurality of processing blocks for determining a feature vector based on characteristics of the input signal and a neural network for determining based on the feature vector whether the impulsive event comprises a speech event or a noise event.
    Type: Grant
    Filed: May 1, 2017
    Date of Patent: November 12, 2019
    Assignee: Cirrus Logic, Inc.
    Inventor: Samuel Pon Varma Ebenezer
  • Patent number: 10453472
    Abstract: A parameter prediction device includes: an environmental characteristic acquirer that acquires an environmental characteristic quantity set which quantifies one or more characteristics of a sound collection environment for an acoustic signal; a target setter that sets a target evaluation value set which provides one or more values obtained by quantifying one or more performances of processing of the acoustic signal, or one or more evaluation values of a processed acoustic signal; and a first predictor that inputs the environmental characteristic quantity set and the target evaluation value set as independent variables to a first prediction model, and predicts a control parameter set for controlling the acoustic signal processing.
    Type: Grant
    Filed: September 22, 2017
    Date of Patent: October 22, 2019
    Assignee: PANASONIC INTELLECTUAL PROPERTY CORPORATION OF AMERICA
    Inventor: Daijiroh Ichimura
  • Patent number: 10453479
    Abstract: A system-effected method for synthesizing speech, or recognizing speech including a sequence of expressive speech utterances. The method can be computer-implemented and can include system-generating a speech signal embodying the sequence of expressive speech utterances. Other possible steps include: system-marking the speech signal with a pitch marker indicating a pitch change at or near a first zero amplitude crossing point of the speech signal following a glottal closure point, at a minimum, at a maximum or at another location; system marking the speech signal with at least one further pitch marker; system-aligning a sequence of prosodically marked text with the pitch-marked speech signal according to the pitch markers; and system outputting the aligned text or the aligned speech signal, respectively. Computerized systems, and stored programs for implementing method embodiments of the invention are also disclosed.
    Type: Grant
    Filed: September 21, 2012
    Date of Patent: October 22, 2019
    Assignee: LESSAC TECHNOLOGIES, INC.
    Inventors: Reiner Wilhelms-Tricarico, Brian Mottershead, Rattima Nitisaroj, Michael Baumgartner, John B. Reichenbach, Gary A. Marple
  • Patent number: 10446162
    Abstract: A very coarse quantization exceeding the measure determined by the masking threshold without or only very little quality losses is enabled by quantizing not immediately the prefiltered signal, but a prediction error obtained by forward-adaptive prediction of the prefiltered signal. Due to the forward adaptivity, the quantizing error has no negative effect on the prediction on the decoder side.
    Type: Grant
    Filed: July 26, 2017
    Date of Patent: October 15, 2019
    Assignee: Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V.
    Inventors: Jens Hirschfeld, Gerald Schuller, Manfred Lutzky, Ulrich Kraemer, Stefan Wabnik
  • Patent number: 10431226
    Abstract: A method for processing a digital audio signal, including a series of samples distributed in consecutive frames, is implemented when decoding the signal in order to replace at least one signal frame lost during decoding. The method includes the following steps: a) searching, in a valid signal segment available when decoding, for at least one period in the signal, determined in accordance with the valid signal; b) analyzing the signal in the period, in order to determine spectral components of the signal in the period; c) synthesizing at least one frame for replacing the lost frame, by construction of a synthesis signal from: an addition of components selected among the predetermined spectral components, and a noise added to the addition of components. In particular, the amount of noise added to the addition of components is weighted in accordance with voice information of the valid signal, obtained when decoding.
    Type: Grant
    Filed: April 24, 2015
    Date of Patent: October 1, 2019
    Assignee: ORANGE
    Inventors: Julien Faure, Stephane Ragot
  • Patent number: 10417268
    Abstract: A keyphrase extraction system and method is provided. The keyphrase extraction system includes a memory having computer-readable instructions stored therein. The keyphrase extraction system also includes a processor configured to access a document. The processor is configured to identify a plurality of candidate phrases from the document based upon a part-of-speech tag pattern. Each of the plurality of candidate phrases comprises one or more candidate terms. In addition, the processor is further configured to access an external knowledge base to determine a vocabulary frequency count of the one or more candidate terms. The vocabulary frequency count of the one or more candidate terms corresponds to a count of appearance of the respective candidate term in a plurality of documents accessible by the external knowledge base.
    Type: Grant
    Filed: December 6, 2017
    Date of Patent: September 17, 2019
    Assignee: Druva Technologies PTE. LTD.
    Inventor: Bhave Adwait
  • Patent number: 10418025
    Abstract: A method for producing speech comprises: accessing an expressive prosody model, wherein the model is generated by: receiving a plurality of non-neutral prosody vector sequences, each vector associated with one of a plurality of time-instances; receiving a plurality of expression labels, each having a time-instance selected from a plurality of non-neutral time-instances of the plurality of time-instances; producing a plurality of neutral prosody vector sequences equivalent to the plurality of non-neutral sequences by applying a linear combination of a plurality of statistical measures to a plurality of sub-sequences selected according to an identified proximity test applied to a plurality of neutral time-instances of the plurality of time-instances; and training at least one machine learning module using the plurality of non-neutral sequences and the plurality of neutral sequences to produce an expressive prosodic model; and using the model within a Text-To-Speech-System to produce an audio waveform from an in
    Type: Grant
    Filed: December 6, 2017
    Date of Patent: September 17, 2019
    Assignee: International Business Machines Corporation
    Inventors: Slava Shechtman, Zvi Kons
  • Patent number: 10402450
    Abstract: A method at an electronic device with an audio input device and an audio output device includes: receiving through the audio input device a verbal input from a user; transmitting information corresponding to the verbal input to a remote system; receiving from the remote system a response responsive to the verbal input, the response including information in accordance with one or more criteria; and outputting the response through the audio output device.
    Type: Grant
    Filed: May 11, 2017
    Date of Patent: September 3, 2019
    Assignee: GOOGLE LLC
    Inventors: Michael Andrew Goodman, Bibo Xu
  • Patent number: 10366696
    Abstract: A linear prediction coefficient of a signal represented in a frequency domain is obtained by performing linear prediction analysis in a frequency direction by using a covariance method or an autocorrelation method. After the filter strength of the obtained linear prediction coefficient is adjusted, filtering may be performed in the frequency direction on the signal by using the adjusted coefficient, whereby the temporal envelope of the signal is shaped. This reduces the occurrence of pre-echo and post-echo and improves the subjective quality of the decoded signal, without significantly increasing the bit rate in a bandwidth extension technique in the frequency domain represented by SBR.
    Type: Grant
    Filed: August 18, 2016
    Date of Patent: July 30, 2019
    Assignee: NTT DOCOMO, INC.
    Inventors: Kosuke Tsujino, Kei Kikuiri, Nobuhiko Naka
  • Patent number: 10360302
    Abstract: A method, computer system, and a computer program product for comparing documents using latent semantic differences is provided. The present invention may include receiving documents from a user. The present invention may also include extracting linguistic units associated with the received documents. The present invention may then include building latent semantic dimensions based on the extracted linguistic units. The present invention may then include weighting the extracted linguistic units utilizing the built latent semantic dimensions. The present invention may then include determining latent semantic differences between the received documents based on weighted linguistic units. The present invention may also include mapping the weighted linguistic units to a scaled visual feature. The present invention may further include generating a visualization to the user of the received documents based on the determined latent semantic differences and the scaled visual feature.
    Type: Grant
    Filed: September 15, 2017
    Date of Patent: July 23, 2019
    Assignee: International Business Machines Corporation
    Inventor: Robert G. Farrell
  • Patent number: 10353480
    Abstract: The present disclosure contemplates a variety of improved methods and systems for enabling set up of a variety of disparate IoT devices coupled to the framework and/or ambient operating system of an assistant device. The described solution includes a voice-driven assistant device setup process. An assistant device can determine the IoT devices in its physical environment and provide setup instructions to the user. The setup including determining voice activatable commands, device information and the adapter to allow the assistant device to operate the one or more IoT devices in response to user instructions.
    Type: Grant
    Filed: May 24, 2017
    Date of Patent: July 16, 2019
    Assignee: ESSENTIAL PRODUCTS, INC.
    Inventors: Manuel Roman, Mara Clair Segal, Dwipal Desai, Andrew E. Rubin
  • Patent number: 10331788
    Abstract: Mechanisms are provided for latent ambiguity handling in natural language processing. The method may include: providing an annotated semantic graph based on a knowledge base in which nodes representing semantic concepts are linked by semantic relationships, wherein one or more nodes are annotated to indicate a latent ambiguity of the semantic concept; processing a natural language input by activation of the annotated semantic graph; during processing when encountering an annotated node indicating a latent ambiguity of the semantic concept, applying a pre-defined latent ambiguity process to the node; and replacing any annotated nodes indicating a latent ambiguity of the concept remaining in an output of the processing of the natural language input with an alternative node from the semantic graph.
    Type: Grant
    Filed: June 22, 2016
    Date of Patent: June 25, 2019
    Assignee: International Business Machines Corporation
    Inventors: Seamus R. McAteer, Daniel J. McCloskey, Mikhail Sogrin
  • Patent number: 10332535
    Abstract: An audio encoder for encoding an audio signal has: a first encoding processor for encoding a first audio signal portion in a frequency domain, having: a time frequency converter for converting the first audio signal portion into a frequency domain representation; an analyzer for analyzing the frequency domain representation to determine first spectral portions to be encoded with a first spectral resolution and second regions to be encoded with a second resolution; and a spectral encoder for encoding the first spectral portions with the first spectral resolution and encoding the second portions with the second resolution; a second encoding processor for encoding a second different audio signal portion in the time domain; a controller for analyzing and determining, which portion of the audio signal is the first audio signal portion encoded in the frequency domain and which portion is the second audio signal portion encoded in the time domain; and an encoded signal former for forming an encoded audio signal havi
    Type: Grant
    Filed: January 24, 2017
    Date of Patent: June 25, 2019
    Assignee: Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.
    Inventors: Sascha Disch, Martin Dietz, Markus Multrus, Guillaume Fuchs, Emmanuel Ravelli, Matthias Neusinger, Markus Schnell, Benjamin Schubert, Bernhard Grill
  • Patent number: 10275461
    Abstract: According to one embodiment of the present invention, a system for converting a display from a source spoken language to a target spoken language includes at least one processor. The at least one processor may be configured to determine the source spoken language of content within a selected area of the display. The at least one processor may be further configured to translate the content from the source spoken language to a selected target spoken language. In addition, the at least one processor may be configured to evaluate the translated content and remap the translated content to the selected area based on the evaluation. Finally, the at least one processor may be configured to present the translated content within the selected area on the display.
    Type: Grant
    Filed: August 5, 2016
    Date of Patent: April 30, 2019
    Assignee: International Business Machines Corporation
    Inventors: Alaa Abou Mahmoud, Paul R. Bastide, Robert E. Loredo, Fang Lu
  • Patent number: 10242678
    Abstract: A friend addition method, device and medium are provided. The method includes: when a voiceprint-based friend addition request is received, target voice information is acquired; user information of a user to be added is determined according to the target voice information; and the user to be added is added as a friend according to the user information.
    Type: Grant
    Filed: June 8, 2017
    Date of Patent: March 26, 2019
    Assignee: BEIJING XIAOMI MOBILE SOFTWARE CO., LTD.
    Inventors: Dalong Shi, Wei Liu, Chao Sun
  • Patent number: 10242696
    Abstract: In accordance with embodiments of the present disclosure, an integrated circuit for implementing at least a portion of an audio device may include an audio output configured to reproduce audio information by generating an audio output signal for communication to at least one transducer of the audio device, a microphone input configured to receive an input signal indicative of ambient sound external to the audio device and a processor configured to implement an impulsive noise detector. The impulsive noise detector may include a sudden onset detector for predicting an occurrence of a signal burst event of the input signal and an impulsive detector for determining whether the signal burst event comprises a speech event or a noise event.
    Type: Grant
    Filed: October 11, 2016
    Date of Patent: March 26, 2019
    Assignee: Cirrus Logic, Inc.
    Inventor: Samuel Pon Varma Ebenezer
  • Patent number: 10210860
    Abstract: Systems and methods are disclosed for customizing a neural network for a custom dataset, when the neural network has been trained on data from a general dataset. The neural network may comprise an output layer including one or more nodes corresponding to candidate outputs. The values of the nodes in the output layer may correspond to a probability that the candidate output is the correct output for an input. The values of the nodes in the output layer may be adjusted for higher performance when the neural network is used to process data from a custom dataset.
    Type: Grant
    Filed: August 22, 2018
    Date of Patent: February 19, 2019
    Assignee: Deepgram, Inc.
    Inventors: Jeff Ward, Adam Sypniewski, Scott Stephenson
  • Patent number: 10210886
    Abstract: A voice starting end detection apparatus includes a first detector that detects a starting end of a voice segment from input signals that are input in a time series, a first transmitting unit that transmits, when the starting end is detected, input signals subsequent to the starting end, and a first receiving unit that receives a terminal end detection signal indicating that a terminal end of the voice segment has been detected. The voice terminal end detection apparatus includes a second receiving unit that receives input signals subsequent to the starting end, a second detector that detects the terminal end from the received input signals, a second transmitting unit that transmits, when the terminal end is detected, the terminal end detection signal. The first transmitting unit stops transmitting the input signals when the first receiving unit receives the terminal end detection signal.
    Type: Grant
    Filed: December 27, 2016
    Date of Patent: February 19, 2019
    Assignee: Kabushiki Kaisha Toshiba
    Inventors: Shoko Miyamori, Mitsuyoshi Tachimori, Kouji Ueno