-
公开(公告)号：US11862142B2
公开(公告)日：2024-01-02
申请号：US17391799
申请日：2021-08-02
申请人： Google LLC
发明人： 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
IPC分类号： G10L13/06 , G10L13/08 , G06N3/08 , G10L25/18 , G10L25/30 , G10L13/04 , G06N3/084 , G10L15/16 , G06N3/045
CPC分类号： G10L13/08 , G06N3/045 , G06N3/08 , G06N3/084 , G10L13/04 , G10L15/16 , G10L25/18 , G10L25/30
摘要： 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.
-
公开(公告)号：US10971170B2
公开(公告)日：2021-04-06
申请号：US16058640
申请日：2018-08-08
申请人： Google LLC
发明人： 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
摘要： 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.
-
公开(公告)号：US10672387B2
公开(公告)日：2020-06-02
申请号：US15839499
申请日：2017-12-12
申请人： GOOGLE LLC
发明人： Richard Lyon , Christopher Hughes , Yuxuan Wang , Ryan Rifkin , Pascal Getreuer
摘要： The various implementations described herein include methods, devices, and systems for recognizing speech, such as user commands. In one aspect, a method includes: (1) receiving audio input data via the one or more microphones; (2) generating a plurality of energy channels for the audio input data; (3) generating a feature vector by performing a per-channel normalization to each channel of the plurality of energy channels; and (4) obtaining recognized speech from the audio input utilizing the feature vector.
-
公开(公告)号：US20210366463A1
公开(公告)日：2021-11-25
申请号：US17391799
申请日：2021-08-02
申请人： Google LLC
发明人： 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
摘要： 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.
-
公开(公告)号：US20200098350A1
公开(公告)日：2020-03-26
申请号：US16696101
申请日：2019-11-26
申请人： Google LLC
发明人： 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
摘要： 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.
-
公开(公告)号：US20190311708A1
公开(公告)日：2019-10-10
申请号：US16447862
申请日：2019-06-20
申请人： Google LLC
发明人： Samy 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
摘要： 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.
-
公开(公告)号：US20180197533A1
公开(公告)日：2018-07-12
申请号：US15839499
申请日：2017-12-12
申请人： GOOGLE LLC
发明人： Richard Lyon , Christopher Hughes , Yuxuan Wang , Ryan Rifkin , Pascal Getreuer
摘要： The various implementations described herein include methods, devices, and systems for recognizing speech, such as user commands. In one aspect, a method includes: (1) receiving audio input data via the one or more microphones; (2) generating a plurality of energy channels for the audio input data; (3) generating a feature vector by performing a per-channel normalization to each channel of the plurality of energy channels; and (4) obtaining recognized speech from the audio input utilizing the feature vector.
-
公开(公告)号：US20240127791A1
公开(公告)日：2024-04-18
申请号：US18516069
申请日：2023-11-21
申请人： Google LLC
发明人： 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
IPC分类号： G10L13/08 , G06N3/045 , G06N3/08 , G06N3/084 , G10L13/04 , G10L15/16 , G10L25/18 , G10L25/30
CPC分类号： G10L13/08 , G06N3/045 , G06N3/08 , G06N3/084 , G10L13/04 , G10L15/16 , G10L25/18 , G10L25/30
摘要： 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.
-
公开(公告)号：US20210295858A1
公开(公告)日：2021-09-23
申请号：US17222736
申请日：2021-04-05
申请人： Google LLC
发明人： 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
摘要： 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.
-
公开(公告)号：US11107457B2
公开(公告)日：2021-08-31
申请号：US16696101
申请日：2019-11-26
申请人： Google LLC
发明人： 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
摘要： 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.
-
-
-
-
-
-
-
-
-
搜索结果
11 条记录 (耗时 0.017 秒)
