公开(公告)号：US20200074985A1

公开(公告)日：2020-03-05

申请号：US16678981

申请日：2019-11-08

Applicant: Google LLC

Inventor： Robert Andrew James Clark ,  Chun-an Chan ,  Vincent Ping Leung Wan

IPC: G10L15/06 ,  G10L15/22 ,  G10L15/16 ,  G10L25/18 ,  G10L25/24 ,  G10L25/21 ,  G10L15/02 ,  G06N3/04 ,  G06N3/08

Abstract: A method for providing a frame-based mel spectral representation of speech includes receiving a text utterance having at least one word, and selecting a mel spectral embedding for the text utterance. Each word in the text utterance has at least one syllable and each syllable has at least one phoneme. For each phoneme, using the selected mel spectral embedding, the method also includes: predicting a duration of the corresponding phoneme by encoding linguistic features of the corresponding phoneme with a corresponding syllable embedding for the syllable that includes the corresponding phoneme; and generating a plurality of fixed-length predicted mel-frequency spectrogram frames based on the predicted duration for the corresponding phoneme. Each fixed-length predicted mel-frequency spectrogram frame representing mel-spectral information of the corresponding phoneme.

公开(公告)号：US12260851B2

公开(公告)日：2025-03-25

申请号：US17305809

申请日：2021-07-14

Applicant: Google LLC

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

IPC: G10L13/00 ,  G10L13/047 ,  G10L13/08

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.

公开(公告)号：US20230064749A1

公开(公告)日：2023-03-02

申请号：US18054604

申请日：2022-11-11

Applicant: Google LLC

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

IPC: G10L13/10 ,  G10L13/02 ,  G10L17/18

Abstract: A method includes receiving an input text utterance to be synthesized into expressive speech having an intended prosody and a target voice and generating, using a first text-to-speech (TTS) model, an intermediate synthesized speech representation for the input text utterance. The intermediate synthesized speech representation possesses the intended prosody. The method also includes providing the intermediate synthesized speech representation to a second TTS model that includes an encoder portion and a decoder portion. The encoder portion is configured to encode the intermediate synthesized speech representation into an utterance embedding that specifies the intended prosody. The decoder portion is configured to process the input text utterance and the utterance embedding to generate an output audio signal of expressive speech that has the intended prosody specified by the utterance embedding and speaker characteristics of the target voice.

公开(公告)号：US11494695B2

公开(公告)日：2022-11-08

申请号：US16586223

申请日：2019-09-27

Applicant: Google LLC

Inventor： Robert Andrew James Clark ,  Chun-an Chan ,  Vincent Ping Leung Wan

IPC: G06N20/00 ,  G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a machine learning model to generate embeddings of inputs to the machine learning model, the machine learning model having an encoder that generates the embeddings from the inputs and a decoder that generates outputs from the generated embeddings, wherein the embedding is partitioned into a sequence of embedding partitions that each includes one or more dimensions of the embedding, the operations comprising: for a first embedding partition in the sequence of embedding partitions: performing initial training to train the encoder and a decoder replica corresponding to the first embedding partition; for each particular embedding partition that is after the first embedding partition in the sequence of embedding partitions: performing incremental training to train the encoder and a decoder replica corresponding to the particular partition.

公开(公告)号：US11264010B2

公开(公告)日：2022-03-01

申请号：US16678981

申请日：2019-11-08

Applicant: Google LLC

Inventor： Robert Andrew James Clark ,  Chun-an Chan ,  Vincent Ping Leung Wan

IPC: G10L25/18 ,  G10L15/06 ,  G10L15/22 ,  G10L15/16 ,  G10L25/24 ,  G10L15/02 ,  G06N3/04 ,  G06N3/08 ,  G10L25/21

Abstract: A method for providing a frame-based mel spectral representation of speech includes receiving a text utterance having at least one word, and selecting a mel spectral embedding for the text utterance. Each word in the text utterance has at least one syllable and each syllable has at least one phoneme. For each phoneme, using the selected mel spectral embedding, the method also includes: predicting a duration of the corresponding phoneme by encoding linguistic features of the corresponding phoneme with a corresponding syllable embedding for the syllable that includes the corresponding phoneme; and generating a plurality of fixed-length predicted mel-frequency spectrogram frames based on the predicted duration for the corresponding phoneme. Each fixed-length predicted mel-frequency spectrogram frame representing mel-spectral information of the corresponding phoneme.

公开(公告)号：US20210134266A1

公开(公告)日：2021-05-06

申请号：US17147548

申请日：2021-01-13

Applicant: Google LLC

Inventor： Robert Clark ,  Chun-an Chan ,  Vincent Wan

IPC: G10L13/10 ,  G10L13/047

Abstract: A method for representing an intended prosody in synthesized speech includes receiving a text utterance having at least one word, and selecting an utterance embedding for the text utterance. Each word in the text utterance has at least one syllable and each syllable has at least one phoneme. The utterance embedding represents an intended prosody. For each syllable, using the selected utterance embedding, the method also includes: predicting a duration of the syllable by encoding linguistic features of each phoneme of the syllable with a corresponding prosodic syllable embedding for the syllable; predicting a pitch contour of the syllable based on the predicted duration for the syllable; and generating a plurality of fixed-length predicted pitch frames based on the predicted duration for the syllable. Each fixed-length predicted pitch frame represents part of the predicted pitch contour of the syllable.

公开(公告)号：US20210097427A1

公开(公告)日：2021-04-01

申请号：US16586223

申请日：2019-09-27

Applicant: Google LLC

Inventor： Robert Andrew James Clark ,  Chun-an Chan ,  Vincent Ping Leung Wan

IPC: G06N20/00 ,  G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a machine learning model to generate embeddings of inputs to the machine learning model, the machine learning model having an encoder that generates the embeddings from the inputs and a decoder that generates outputs from the generated embeddings, wherein the embedding is partitioned into a sequence of embedding partitions that each includes one or more dimensions of the embedding, the operations comprising: for a first embedding partition in the sequence of embedding partitions: performing initial training to train the encoder and a decoder replica corresponding to the first embedding partition; for each particular embedding partition that is after the first embedding partition in the sequence of embedding partitions: performing incremental training to train the encoder and a decoder replica corresponding to the particular partition.

公开(公告)号：US10923107B2

公开(公告)日：2021-02-16

申请号：US16382722

申请日：2019-04-12

Applicant: Google LLC

Inventor： Robert Clark ,  Chun-an Chan ,  Vincent Wan

IPC: G10L13/10 ,  G10L13/047

Abstract: A method for representing an intended prosody in synthesized speech includes receiving a text utterance having at least one word, and selecting an utterance embedding for the text utterance. Each word in the text utterance has at least one syllable and each syllable has at least one phoneme. The utterance embedding represents an intended prosody. For each syllable, using the selected utterance embedding, the method also includes: predicting a duration of the syllable by encoding linguistic features of each phoneme of the syllable with a corresponding prosodic syllable embedding for the syllable; predicting a pitch contour of the syllable based on the predicted duration for the syllable; and generating a plurality of fixed-length predicted pitch frames based on the predicted duration for the syllable. Each fixed-length predicted pitch frame represents part of the predicted pitch contour of the syllable.