公开(公告)号：US20230058658A1

公开(公告)日：2023-02-23

申请号：US17882691

申请日：2022-08-08

Applicant: Amazon Technologies, Inc.

Inventor： Jaime Lorenzo Trueba ,  Thomas Renaud Drugman ,  Viacheslav Klimkov ,  Srikanth Ronanki ,  Thomas Edward Merritt ,  Andrew Paul Breen ,  Roberto Barra-Chicote

IPC: G10L13/10 ,  G10L25/18 ,  G10L13/06

Abstract: During text-to-speech processing, a speech model creates output audio data, including speech, that corresponds to input text data that includes a representation of the speech. A spectrogram estimator estimates a frequency spectrogram of the speech; the corresponding frequency-spectrogram data is used to condition the speech model. A plurality of acoustic features corresponding to different segments of the input text data, such as phonemes, syllable-level features, and/or word-level features, may be separately encoded into context vectors; the spectrogram estimator uses these separate context vectors to create the frequency spectrogram.

公开(公告)号：US11410639B2

公开(公告)日：2022-08-09

申请号：US16922590

申请日：2020-07-07

Applicant: Amazon Technologies, Inc.

Inventor： Jaime Lorenzo Trueba ,  Thomas Renaud Drugman ,  Viacheslav Klimkov ,  Srikanth Ronanki ,  Thomas Edward Merritt ,  Andrew Paul Breen ,  Roberto Barra-Chicote

IPC: G10L13/10 ,  G10L25/18 ,  G10L13/06

Abstract: During text-to-speech processing, a speech model creates output audio data, including speech, that corresponds to input text data that includes a representation of the speech. A spectrogram estimator estimates a frequency spectrogram of the speech; the corresponding frequency-spectrogram data is used to condition the speech model. A plurality of acoustic features corresponding to different segments of the input text data, such as phonemes, syllable-level features, and/or word-level features, may be separately encoded into context vectors; the spectrogram estimator uses these separate context vectors to create the frequency spectrogram.

公开(公告)号：US10741169B1

公开(公告)日：2020-08-11

申请号：US16141241

申请日：2018-09-25

Applicant: Amazon Technologies, Inc.

Inventor： Jaime Lorenzo Trueba ,  Thomas Renaud Drugman ,  Viacheslav Klimkov ,  Srikanth Ronanki ,  Thomas Edward Merritt ,  Andrew Paul Breen ,  Roberto Barra-Chicote

IPC: G10L13/08 ,  G10L13/10 ,  G10L25/18 ,  G10L13/06

Abstract: During text-to-speech processing, a speech model creates output audio data, including speech, that corresponds to input text data that includes a representation of the speech. A spectrogram estimator estimates a frequency spectrogram of the speech; the corresponding frequency-spectrogram data is used to condition the speech model. A plurality of acoustic features corresponding to different segments of the input text data, such as phonemes, syllable-level features, and/or word-level features, may be separately encoded into context vectors; the spectrogram estimator uses these separate context vectors to create the frequency spectrogram.