Patents by Inventor Ron J. Weiss
Ron J. Weiss has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20220005465Abstract: A method for performing speech recognition using sequence-to-sequence models includes receiving audio data for an utterance and providing features indicative of acoustic characteristics of the utterance as input to an encoder. The method also includes processing an output of the encoder using an attender to generate a context vector, generating speech recognition scores using the context vector and a decoder trained using a training process, and generating a transcription for the utterance using word elements selected based on the speech recognition scores. The transcription is provided as an output of the ASR system.Type: ApplicationFiled: September 20, 2021Publication date: January 6, 2022Applicant: Google LLCInventors: Rohit Prakash Prabhavalkar, Zhifeng Chen, Bo Li, Chung-cheng Chiu, Kanury Kanishka Rao, Yonghui Wu, Ron J. Weiss, Navdeep Jaitly, Michiel A.u. Bacchiani, Tara N. Sainath, Jan Kazimierz Chorowski, Anjuli Patricia Kannan, Ekaterina Gonina, Patrick An Phu Nguyen
-
Publication number: 20210366463Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.Type: ApplicationFiled: August 2, 2021Publication date: November 25, 2021Inventors: Samuel Bengio, Yuxuan Wang, Zongheng Yang, Zhifeng Chen, Yonghui Wu, Ioannis Agiomyrgiannakis, Ron J. Weiss, Navdeep Jaitly, Ryan M. Rifkin, Robert Andrew James Clark, Quoc V. Le, Russell J. Ryan, Ying Xiao
-
Patent number: 11145293Abstract: Methods, systems, and apparatus, including computer-readable media, for performing speech recognition using sequence-to-sequence models. An automated speech recognition (ASR) system receives audio data for an utterance and provides features indicative of acoustic characteristics of the utterance as input to an encoder. The system processes an output of the encoder using an attender to generate a context vector and generates speech recognition scores using the context vector and a decoder trained using a training process that selects at least one input to the decoder with a predetermined probability. An input to the decoder during training is selected between input data based on a known value for an element in a training example, and input data based on an output of the decoder for the element in the training example. A transcription is generated for the utterance using word elements selected based on the speech recognition scores. The transcription is provided as an output of the ASR system.Type: GrantFiled: July 19, 2019Date of Patent: October 12, 2021Assignee: Google LLCInventors: Rohit Prakash Prabhavalkar, Zhifeng Chen, Bo Li, Chung-Cheng Chiu, Kanury Kanishka Rao, Yonghui Wu, Ron J. Weiss, Navdeep Jaitly, Michiel A. U. Bacchiani, Tara N. Sainath, Jan Kazimierz Chorowski, Anjuli Patricia Kannan, Ekaterina Gonina, Patrick An Phu Nguyen
-
Publication number: 20210295858Abstract: Methods, systems, and computer program products for generating, from an input character sequence, an output sequence of audio data representing the input character sequence. The output sequence of audio data includes a respective audio output sample for each of a number of time steps. One example method includes, for each of the time steps: generating a mel-frequency spectrogram for the time step by processing a representation of a respective portion of the input character sequence using a decoder neural network; generating a probability distribution over a plurality of possible audio output samples for the time step by processing the mel-frequency spectrogram for the time step using a vocoder neural network; and selecting the audio output sample for the time step from the possible audio output samples in accordance with the probability distribution.Type: ApplicationFiled: April 5, 2021Publication date: September 23, 2021Inventors: Yonghui Wu, Jonathan Shen, Ruoming Pang, Ron J. Weiss, Michael Schuster, Navdeep Jaitly, Zongheng Yang, Zhifeng Chen, Yu Zhang, Yuxuan Wang, Russell John Wyatt Skerry-Ryan, Ryan M. Rifkin, Ioannis Agiomyrgiannakis
-
Publication number: 20210295859Abstract: This specification describes computer-implemented methods and systems. One method includes receiving, by a neural network of a speech recognition system, first data representing a first raw audio signal and second data representing a second raw audio signal. The first raw audio signal and the second raw audio signal describe audio occurring at a same period of time. The method further includes generating, by a spatial filtering layer of the neural network, a spatial filtered output using the first data and the second data, and generating, by a spectral filtering layer of the neural network, a spectral filtered output using the spatial filtered output. Generating the spectral filtered output comprises processing frequency-domain data representing the spatial filtered output. The method still further includes processing, by one or more additional layers of the neural network, the spectral filtered output to predict sub-word units encoded in both the first raw audio signal and the second raw audio signal.Type: ApplicationFiled: June 8, 2021Publication date: September 23, 2021Applicant: Google LLCInventors: Ehsan Variani, Kevin William Wilson, Ron J. Weiss, Tara N. Sainath, Arun Narayanan
-
Patent number: 11107457Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.Type: GrantFiled: November 26, 2019Date of Patent: August 31, 2021Assignee: Google LLCInventors: Samuel Bengio, Yuxuan Wang, Zongheng Yang, Zhifeng Chen, Yonghui Wu, Ioannis Agiomyrgiannakis, Ron J. Weiss, Navdeep Jaitly, Ryan M. Rifkin, Robert Andrew James Clark, Quoc V. Le, Russell J. Ryan, Ying Xiao
-
Patent number: 11080589Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a target sequence including a respective output at each of multiple output time steps from respective encoded representations of inputs in an input sequence. The method includes, for each output time step, starting from the position, in the input order, of the encoded representation that was selected as a preceding context vector at a preceding output time step, traversing the encoded representations until an encoded representation is selected as a current context vector at the output time step. A decoder neural network processes the current context vector and a preceding output at the preceding output time step to generate a respective output score for each possible output and to update the hidden state of the decoder recurrent neural network. An output is selected for the output time step using the output scores.Type: GrantFiled: July 8, 2019Date of Patent: August 3, 2021Assignee: Google LLCInventors: Ron J. Weiss, Thang Minh Luong, Peter J. Liu, Colin Abraham Raffel, Douglas Eck
-
Publication number: 20210217404Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech synthesis. The methods, systems, and apparatus include actions of obtaining an audio representation of speech of a target speaker, obtaining input text for which speech is to be synthesized in a voice of the target speaker, generating a speaker vector by providing the audio representation to a speaker encoder engine that is trained to distinguish speakers from one another, generating an audio representation of the input text spoken in the voice of the target speaker by providing the input text and the speaker vector to a spectrogram generation engine that is trained using voices of reference speakers to generate audio representations, and providing the audio representation of the input text spoken in the voice of the target speaker for output.Type: ApplicationFiled: May 17, 2019Publication date: July 15, 2021Applicant: Google LLCInventors: Ye Jia, Zhifeng Chen, Yonghui Wu, Jonathan Shen, Ruoming Pang, Ron J. Weiss, Ignacio Lopez Moreno, Fei Ren, Yu Zhang, Quan Wang, Patrick Nguyen
-
Patent number: 11062725Abstract: This specification describes computer-implemented methods and systems. One method includes receiving, by a neural network of a speech recognition system, first data representing a first raw audio signal and second data representing a second raw audio signal. The first raw audio signal and the second raw audio signal describe audio occurring at a same period of time. The method further includes generating, by a spatial filtering layer of the neural network, a spatial filtered output using the first data and the second data, and generating, by a spectral filtering layer of the neural network, a spectral filtered output using the spatial filtered output. Generating the spectral filtered output comprises processing frequency-domain data representing the spatial filtered output. The method still further includes processing, by one or more additional layers of the neural network, the spectral filtered output to predict sub-word units encoded in both the first raw audio signal and the second raw audio signal.Type: GrantFiled: February 19, 2019Date of Patent: July 13, 2021Assignee: Google LLCInventors: Ehsan Variani, Kevin William Wilson, Ron J. Weiss, Tara N. Sainath, Arun Narayanan
-
Patent number: 10971170Abstract: Methods, systems, and computer program products for generating, from an input character sequence, an output sequence of audio data representing the input character sequence. The output sequence of audio data includes a respective audio output sample for each of a number of time steps. One example method includes, for each of the time steps: generating a mel-frequency spectrogram for the time step by processing a representation of a respective portion of the input character sequence using a decoder neural network; generating a probability distribution over a plurality of possible audio output samples for the time step by processing the mel-frequency spectrogram for the time step using a vocoder neural network; and selecting the audio output sample for the time step from the possible audio output samples in accordance with the probability distribution.Type: GrantFiled: August 8, 2018Date of Patent: April 6, 2021Assignee: Google LLCInventors: Yonghui Wu, Jonathan Shen, Ruoming Pang, Ron J. Weiss, Michael Schuster, Navdeep Jaitly, Zongheng Yang, Zhifeng Chen, Yu Zhang, Yuxuan Wang, Russell John Wyatt Skerry-Ryan, Ryan M. Rifkin, Ioannis Agiomyrgiannakis
-
Patent number: 10930270Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing audio waveforms. In some implementations, a time-frequency feature representation is generated based on audio data. The time-frequency feature representation is input to an acoustic model comprising a trained artificial neural network. The trained artificial neural network comprising a frequency convolution layer, a memory layer, and one or more hidden layers. An output that is based on output of the trained artificial neural network is received. A transcription is provided, where the transcription is determined based on the output of the acoustic model.Type: GrantFiled: August 15, 2019Date of Patent: February 23, 2021Assignee: Google LLCInventors: Tara N. Sainath, Ron J. Weiss, Andrew W. Senior, Kevin William Wilson
-
Publication number: 20200380952Abstract: A method includes receiving an input text sequence to be synthesized into speech in a first language and obtaining a speaker embedding, the speaker embedding specifying specific voice characteristics of a target speaker for synthesizing the input text sequence into speech that clones a voice of the target speaker. The target speaker includes a native speaker of a second language different than the first language. The method also includes generating, using a text-to-speech (TTS) model, an output audio feature representation of the input text by processing the input text sequence and the speaker embedding. The output audio feature representation includes the voice characteristics of the target speaker specified by the speaker embedding.Type: ApplicationFiled: April 22, 2020Publication date: December 3, 2020Applicant: Google LLCInventors: Yu Zhang, Ron J. Weiss, Byungha Chun, Yonghui Wu, Zhifeng Chen, Russell John Wyatt Skerry-Ryan, Ye Jia, Andrew M. Rosenberg, Bhuvana Ramabhadran
-
Publication number: 20200160836Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer-readable media, for speech recognition using multi-dialect and multilingual models. In some implementations, audio data indicating audio characteristics of an utterance is received. Input features determined based on the audio data are provided to a speech recognition model that has been trained to output score indicating the likelihood of linguistic units for each of multiple different language or dialects. The speech recognition model can be one that has been trained using cluster adaptive training. Output that the speech recognition model generated in response to receiving the input features determined based on the audio data is received. A transcription of the utterance generated based on the output of the speech recognition model is provided.Type: ApplicationFiled: November 14, 2019Publication date: May 21, 2020Inventors: Zhifeng Chen, Bo Li, Eugene Weinstein, Yonghui Wu, Pedro J. Moreno Mengibar, Ron J. Weiss, Khe Chai Sim, Tara N. Sainath, Patrick An Phu Nguyen
-
Publication number: 20200118553Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for neural network adaptive beamforming for multichannel speech recognition are disclosed. In one aspect, a method includes the actions of receiving a first channel of audio data corresponding to an utterance and a second channel of audio data corresponding to the utterance. The actions further include generating a first set of filter parameters for a first filter based on the first channel of audio data and the second channel of audio data and a second set of filter parameters for a second filter based on the first channel of audio data and the second channel of audio data. The actions further include generating a single combined channel of audio data. The actions further include inputting the audio data to a neural network. The actions further include providing a transcription for the utterance.Type: ApplicationFiled: December 10, 2019Publication date: April 16, 2020Inventors: Bo Li, Ron J. Weiss, Michiel A.U. Bacchiani, Tara N. Sainath, Kevin William Wilson
-
Publication number: 20200098350Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.Type: ApplicationFiled: November 26, 2019Publication date: March 26, 2020Inventors: Samuel Bengio, Yuxuan Wang, Zongheng Yang, Zhifeng Chen, Yonghui Wu, Ioannis Agiomyrgiannakis, Ron J. Weiss, Navdeep Jaitly, Ryan M. Rifkin, Robert Andrew James Clark, Quoc V. Le, Russell J. Ryan, Ying Xiao
-
Patent number: 10573293Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.Type: GrantFiled: June 20, 2019Date of Patent: February 25, 2020Assignee: Google LLCInventors: Samuel Bengio, Yuxuan Wang, Zongheng Yang, Zhifeng Chen, Yonghui Wu, Ioannis Agiomyrgiannakis, Ron J. Weiss, Navdeep Jaitly, Ryan M. Rifkin, Robert Andrew James Clark, Quoc V. Le, Russell J. Ryan, Ying Xiao
-
Publication number: 20200051583Abstract: Methods, systems, and computer program products for generating, from an input character sequence, an output sequence of audio data representing the input character sequence. The output sequence of audio data includes a respective audio output sample for each of a number of time steps. One example method includes, for each of the time steps: generating a mel-frequency spectrogram for the time step by processing a representation of a respective portion of the input character sequence using a decoder neural network; generating a probability distribution over a plurality of possible audio output samples for the time step by processing the mel-frequency spectrogram for the time step using a vocoder neural network; and selecting the audio output sample for the time step from the possible audio output samples in accordance with the probability distribution.Type: ApplicationFiled: August 8, 2018Publication date: February 13, 2020Inventors: Yonghui Wu, Jonathan Shen, Ruoming Pang, Ron J. Weiss
-
Publication number: 20200027444Abstract: Methods, systems, and apparatus, including computer-readable media, for performing speech recognition using sequence-to-sequence models. An automated speech recognition (ASR) system receives audio data for an utterance and provides features indicative of acoustic characteristics of the utterance as input to an encoder. The system processes an output of the encoder using an attender to generate a context vector and generates speech recognition scores using the context vector and a decoder trained using a training process that selects at least one input to the decoder with a predetermined probability. An input to the decoder during training is selected between input data based on a known value for an element in a training example, and input data based on an output of the decoder for the element in the training example. A transcription is generated for the utterance using word elements selected based on the speech recognition scores. The transcription is provided as an output of the ASR system.Type: ApplicationFiled: July 19, 2019Publication date: January 23, 2020Inventors: Rohit Prakash Prabhavalkar, Zhifeng Chen, Bo Li, Chung-Cheng Chiu, Kanury Kanishka Rao, Yonghui Wu, Ron J. Weiss, Navdeep Jaitly, Michiel A.U. Bacchiani, Tara N. Sainath, Jan Kazimierz Chorowski, Anjuli Patricia Kannan, Ekaterina Gonina, Patrick An Phu Nguyen
-
Patent number: 10515626Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for neural network adaptive beamforming for multichannel speech recognition are disclosed. In one aspect, a method includes the actions of receiving a first channel of audio data corresponding to an utterance and a second channel of audio data corresponding to the utterance. The actions further include generating a first set of filter parameters for a first filter based on the first channel of audio data and the second channel of audio data and a second set of filter parameters for a second filter based on the first channel of audio data and the second channel of audio data. The actions further include generating a single combined channel of audio data. The actions further include inputting the audio data to a neural network. The actions further include providing a transcription for the utterance.Type: GrantFiled: December 20, 2017Date of Patent: December 24, 2019Assignee: Google LLCInventors: Bo Li, Ron J. Weiss, Michiel A. U. Bacchiani, Tara N. Sainath, Kevin William Wilson
-
Publication number: 20190378498Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing audio waveforms. In some implementations, a time-frequency feature representation is generated based on audio data. The time-frequency feature representation is input to an acoustic model comprising a trained artificial neural network. The trained artificial neural network comprising a frequency convolution layer, a memory layer, and one or more hidden layers. An output that is based on output of the trained artificial neural network is received. A transcription is provided, where the transcription is determined based on the output of the acoustic model.Type: ApplicationFiled: August 15, 2019Publication date: December 12, 2019Inventors: Tara N. Sainath, Ron J. Weiss, Andrew W. Senior, Kevin William Wilson