-
公开(公告)号：US11017763B1
公开(公告)日：2021-05-25
申请号：US16712466
申请日：2019-12-12
IPC分类号： G10L15/22 , G10L15/26 , G10L13/08 , G10L13/047 , G10L13/033
摘要： During text-to-speech processing, a sequence-to-sequence neural network model may process text data and determine corresponding spectrogram data. A normalizing flow component may then process this spectrogram data to predict corresponding phase data. An inverse Fourier transform may then be performed on the spectrogram and phase data to create an audio waveform that includes speech corresponding to the text.
-
公开(公告)号：US20230043916A1
公开(公告)日：2023-02-09
申请号：US17848831
申请日：2022-06-24
发明人： Roberto Barra Chicote , Vatsal Aggarwal , Andrew Paul Breen , Javier Gonzalez Hernandez , Nishant Prateek
IPC分类号： G10L13/10 , G06F40/30 , G10L13/033 , G10L13/047
摘要： During text-to-speech processing, a speech model creates synthesized speech that corresponds to input data. The speech model may include an encoder for encoding the input data into a context vector and a decoder for decoding the context vector into spectrogram data. The speech model may further include a voice decoder that receives vocal characteristic data representing a desired vocal characteristic of synthesized speech. The voice decoder may process the vocal characteristic data to determine configuration data, such as weights, for use by the speech decoder.
-
公开(公告)号：US10692484B1
公开(公告)日：2020-06-23
申请号：US16007757
申请日：2018-06-13
发明人： Thomas Edward Merritt , Adam Franciszek Nadolski , Nishant Prateek , Bartosz Putrycz , Roberto Barra Chicote , Vatsal Aggarwal , Andrew Paul Breen
IPC分类号： G10L13/04 , G10L13/08 , G10L25/24 , G10L25/60 , G10L13/047
摘要： A speech model is trained using multi-task learning. A first task may correspond to how well predicted audio matches training audio; a second task may correspond to a metric of perceived audio quality. The speech model may include, during training, layers related to the second task that are discarded at runtime.
-
公开(公告)号：US11373633B2
公开(公告)日：2022-06-28
申请号：US16586007
申请日：2019-09-27
发明人： Roberto Barra Chicote , Vatsal Aggarwal , Andrew Paul Breen , Javier Gonzalez Hernandez , Nishant Prateek
IPC分类号： G10L13/033 , G10L13/047 , G10L15/18 , G10L13/10 , G06F40/30
摘要： During text-to-speech processing, a speech model creates synthesized speech that corresponds to input data. The speech model may include an encoder for encoding the input data into a context vector and a decoder for decoding the context vector into spectrogram data. The speech model may further include a voice decoder that receives vocal characteristic data representing a desired vocal characteristic of synthesized speech. The voice decoder may process the vocal characteristic data to determine configuration data, such as weights, for use by the speech decoder.
-
公开(公告)号：US20210097976A1
公开(公告)日：2021-04-01
申请号：US16586007
申请日：2019-09-27
发明人： Roberto Barra Chicote , Vatsal Aggarwal , Andrew Paul Breen , Javier Gonzalez Hernandez , Nishant Prateek
IPC分类号： G10L13/10 , G10L13/047 , G06F17/27 , G10L13/033
摘要： During text-to-speech processing, a speech model creates synthesized speech that corresponds to input data. The speech model may include an encoder for encoding the input data into a context vector and a decoder for decoding the context vector into spectrogram data. The speech model may further include a voice decoder that receives vocal characteristic data representing a desired vocal characteristic of synthesized speech. The voice decoder may process the vocal characteristic data to determine configuration data, such as weights, for use by the speech decoder.
-
-
-
-
搜索结果
5 条记录 (耗时 0.012 秒)
