中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

90 records (took 0.021 seconds)

    Building a Text-to-Speech System from a Small Amount of Speech Data
    11.
    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

    Applicant: Google LLC

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

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

    Abstract: 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.

    VERY DEEP CONVOLUTIONAL NEURAL NETWORKS FOR END-TO-END SPEECH RECOGNITION
    14.
    发明申请
    VERY DEEP CONVOLUTIONAL NEURAL NETWORKS FOR END-TO-END SPEECH RECOGNITION 审中-公开

    公开(公告)号：US20190236451A1

    公开(公告)日：2019-08-01

    申请号：US16380101

    申请日：2019-04-10

    Applicant: Google LLC

    Inventor： Navdeep Jaitly ,  Yu Zhang ,  William Chan

    IPC: G06N3/08 ,  G06N3/04 ,  G10L15/16 ,  G10L15/02 ,  G10L15/22

    Abstract: A speech recognition neural network system includes an encoder neural network and a decoder neural network. The encoder neural network generates an encoded sequence from an input acoustic sequence that represents an utterance. The input acoustic sequence includes a respective acoustic feature representation at each of a plurality of input time steps, the encoded sequence includes a respective encoded representation at each of a plurality of time reduced time steps, and the number of time reduced time steps is less than the number of input time steps. The encoder neural network includes a time reduction subnetwork, a convolutional LSTM subnetwork, and a network in network subnetwork. The decoder neural network receives the encoded sequence and processes the encoded sequence to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings.

    Supervised and Unsupervised Training with Contrastive Loss Over Sequences
    15.
    发明申请
    Supervised and Unsupervised Training with Contrastive Loss Over Sequences 有权

    公开(公告)号：US20250166614A1

    公开(公告)日：2025-05-22

    申请号：US19034304

    申请日：2025-01-22

    Applicant: Google LLC

    Inventor： Andrew Rosenberg ,  Bhuvana Ramabhadran ,  Zhehuai Chen ,  Yuan Wang ,  Yu Zhang ,  Jesse Emond

    IPC: G10L15/06 ,  G06N3/0464 ,  G06N3/09

    Abstract: A method includes receiving audio data corresponding to an utterance and generating a pair of positive audio data examples. Here, each positive audio data example includes a respective augmented copy of the received audio data. For each respective positive audio data example, the method includes generating a respective sequence of encoder outputs and projecting the respective sequence of encoder outputs for the positive data example into a contrastive loss space. The method also includes determining a L2 distance between each corresponding encoder output in the projected sequences of encoder outputs for the positive audio data examples and determining a per-utterance consistency loss by averaging the L2 distances. The method also includes generating corresponding speech recognition results for each respective positive audio data example. The method also includes updating parameters of the speech recognition model based on a respective supervised loss term and the per-utterance consistency loss.

    Two-Level Text-To-Speech Systems Using Synthetic Training Data
    16.
    发明申请
    Two-Level Text-To-Speech Systems Using Synthetic Training Data 有权

    公开(公告)号：US20250078808A1

    公开(公告)日：2025-03-06

    申请号：US18949095

    申请日：2024-11-15

    Applicant: Google LLC

    Inventor： Lev Finkelstein ,  Chun-an Chan ,  Byungha Chun ,  Norman Casagrande ,  Yu Zhang ,  Robert Andrew James Clark ,  Vincent Wan

    IPC: G10L13/08 ,  G10L13/047

    Abstract: A method includes obtaining training data including a plurality of training audio signals and corresponding transcripts. Each training audio signal is spoken by a target speaker in a first accent/dialect. For each training audio signal of the training data, the method includes generating a training synthesized speech representation spoken by the target speaker in a second accent/dialect different than the first accent/dialect and training a text-to-speech (TTS) system based on the corresponding transcript and the training synthesized speech representation. The method also includes receiving an input text utterance to be synthesized into speech in the second accent/dialect. The method also includes obtaining conditioning inputs that include a speaker embedding and an accent/dialect identifier that identifies the second accent/dialect. The method also includes generating an output audio waveform corresponding to a synthesized speech representation of the input text sequence that clones the voice of the target speaker in the second accent/dialect.

    Injecting Text in Self-Supervised Speech Pre-training
    17.
    发明申请
    Injecting Text in Self-Supervised Speech Pre-training 有权

    公开(公告)号：US20250078807A1

    公开(公告)日：2025-03-06

    申请号：US18951572

    申请日：2024-11-18

    Applicant: Google LLC

    Inventor： Zhehuai Chen ,  Bhuvana Ramabhadran ,  Andrew M. Rosenberg ,  Yu Zhang ,  Pedro J. Moreno Mengibar

    IPC: G10L13/047 ,  G10L13/08

    Abstract: A method includes receiving training data that includes unspoken text utterances and un-transcribed non-synthetic speech utterances. Each unspoken text utterance is not paired with any corresponding spoken utterance of non-synthetic speech. Each un-transcribed non-synthetic speech utterance is not paired with a corresponding transcription. The method also includes generating a corresponding synthetic speech representation for each unspoken textual utterance of the received training data using a text-to-speech model. The method also includes pre-training an audio encoder on the synthetic speech representations generated for the unspoken textual utterances and the un-transcribed non-synthetic speech utterances to teach the audio encoder to jointly learn shared speech and text representations.

Patent Agency Ranking