利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

29 条记录 (耗时 0.017 秒)

    Building a Text-to-Speech System from a Small Amount of Speech Data
    2.
    发明申请
    Building a Text-to-Speech System from a Small Amount of Speech Data 有权

    公开(公告)号：US20220068256A1

    公开(公告)日：2022-03-03

    申请号：US17005974

    申请日：2020-08-28

    申请人： Google LLC

    发明人： Ye Jia ,  Byungha Chun ,  Yusuke Oda ,  Norman Casagrande ,  Tejas Iyer ,  Fan Luo ,  Russell John Wyatt Skerry-Ryan ,  Jonathan Shen ,  Yonghui Wu ,  Yu Zhang

    IPC分类号： G10L13/04 ,  G10L13/033 ,  G10L13/08 ,  G10L15/06

    摘要： A method of building a text-to-speech (TTS) system from a small amount of speech data includes receiving a first plurality of recorded speech samples from an assortment of speakers and a second plurality of recorded speech samples from a target speaker where the assortment of speakers does not include the target speaker. The method further includes training a TTS model using the first plurality of recorded speech samples from the assortment of speakers. Here, the trained TTS model is configured to output synthetic speech as an audible representation of a text input. The method also includes re-training the trained TTS model using the second plurality of recorded speech samples from the target speaker combined with the first plurality of recorded speech samples from the assortment of speakers. Here, the re-trained TTS model is configured to output synthetic speech resembling speaking characteristics of the target speaker.

    Unsupervised parallel tacotron non-autoregressive and controllable text-to-speech
    3.
    发明授权
    Unsupervised parallel tacotron non-autoregressive and controllable text-to-speech 有权

    公开(公告)号：US11823656B2

    公开(公告)日：2023-11-21

    申请号：US17326542

    申请日：2021-05-21

    申请人： Google LLC

    发明人： Isaac Elias ,  Byungha Chun ,  Jonathan Shen ,  Ye Jia ,  Yu Zhang ,  Yonghui Wu

    IPC分类号： G10L13/08 ,  G10L13/04

    CPC分类号： G10L13/08 ,  G10L13/04

    摘要： A method for training a non-autoregressive TTS model includes obtaining a sequence representation of an encoded text sequence concatenated with a variational embedding. The method also includes using a duration model network to predict a phoneme duration for each phoneme represented by the encoded text sequence. Based on the predicted phoneme durations, the method also includes learning an interval representation and an auxiliary attention context representation. The method also includes upsampling, using the interval representation and the auxiliary attention context representation, the sequence representation into an upsampled output specifying a number of frames. The method also includes generating, based on the upsampled output, one or more predicted mel-frequency spectrogram sequences for the encoded text sequence. The method also includes determining a final spectrogram loss based on the predicted mel-frequency spectrogram sequences and a reference mel-frequency spectrogram sequence and training the TTS model based on the final spectrogram loss.

    Robust Direct Speech-to-Speech Translation
    7.
    发明公开
    Robust Direct Speech-to-Speech Translation 审中-公开

    公开(公告)号：US20240273311A1

    公开(公告)日：2024-08-15

    申请号：US18626745

    申请日：2024-04-04

    申请人： Google LLC

    发明人： Ye Jia ,  Michelle Tadmor Ramanovich ,  Tal Remez ,  Roi Pomerantz

    IPC分类号： G06F40/58 ,  G10L13/02 ,  G10L13/10 ,  G10L19/16

    CPC分类号： G06F40/58 ,  G10L13/02 ,  G10L13/10 ,  G10L19/16

    摘要： A direct speech-to-speech translation (S2ST) model includes an encoder configured to receive an input speech representation that to an utterance spoken by a source speaker in a first language and encode the input speech representation into a hidden feature representation. The S2ST model also includes an attention module configured to generate a context vector that attends to the hidden representation encoded by the encoder. The S2ST model also includes a decoder configured to receive the context vector generated by the attention module and predict a phoneme representation that corresponds to a translation of the utterance in a second different language. The S2ST model also includes a synthesizer configured to receive the context vector and the phoneme representation and generate a translated synthesized speech representation that corresponds to a translation of the utterance spoken in the different second language.

    Robust direct speech-to-speech translation
    9.
    发明授权
    Robust direct speech-to-speech translation 有权

    公开(公告)号：US11960852B2

    公开(公告)日：2024-04-16

    申请号：US17644351

    申请日：2021-12-15

    申请人： Google LLC

    发明人： Ye Jia ,  Michelle Tadmor Ramanovich ,  Tal Remez ,  Roi Pomerantz

    IPC分类号： G06F40/58 ,  G10L13/02 ,  G10L13/10 ,  G10L19/16

    CPC分类号： G06F40/58 ,  G10L13/02 ,  G10L13/10 ,  G10L19/16

    摘要： A direct speech-to-speech translation (S2ST) model includes an encoder configured to receive an input speech representation that to an utterance spoken by a source speaker in a first language and encode the input speech representation into a hidden feature representation. The S2ST model also includes an attention module configured to generate a context vector that attends to the hidden representation encoded by the encoder. The S2ST model also includes a decoder configured to receive the context vector generated by the attention module and predict a phoneme representation that corresponds to a translation of the utterance in a second different language. The S2ST model also includes a synthesizer configured to receive the context vector and the phoneme representation and generate a translated synthesized speech representation that corresponds to a translation of the utterance spoken in the different second language.