-
公开(公告)号：US10249289B2
公开(公告)日：2019-04-02
申请号：US15649311
申请日：2017-07-13
Applicant: Google LLC
Inventor： Byung Ha Chun , Javier Gonzalvo , Chun-an Chan , Ioannis Agiomyrgiannakis , Vincent Ping Leung Wan , Robert Andrew James Clark , Jakub Vit
IPC: G10L13/06 , G10L19/00 , G10L25/30 , G10L13/027 , G10L13/047
Abstract: Methods, systems, and computer-readable media for text-to-speech synthesis using an autoencoder. In some implementations, data indicating a text for text-to-speech synthesis is obtained. Data indicating a linguistic unit of the text is provided as input to an encoder. The encoder is configured to output speech unit representations indicative of acoustic characteristics based on linguistic information. A speech unit representation that the encoder outputs is received. A speech unit is selected to represent the linguistic unit, the speech unit being selected from among a collection of speech units based on the speech unit representation output by the encoder. Audio data for a synthesized utterance of the text that includes the selected speech unit is provided.
-
公开(公告)号：US20240038214A1
公开(公告)日：2024-02-01
申请号：US18487227
申请日：2023-10-16
Applicant: Google LLC
Inventor： Robert Clark , Chun-an Chan , Vincent Wan
CPC classification number: G10L13/10 , G10L25/30 , G10L2013/105
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 decoding a prosodic syllable embedding for the syllable based on attention by an attention mechanism to linguistic features of each phoneme of the syllable and generating a plurality of fixed-length predicted frames based on the predicted duration for the syllable.
-
公开(公告)号：US11790274B2
公开(公告)日：2023-10-17
申请号：US18049995
申请日：2022-10-26
Applicant: Google LLC
Inventor： Robert Andrew James Clark , Chun-an Chan , Vincent Ping Leung Wan
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：US20230018384A1
公开(公告)日：2023-01-19
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: G10L13/08 , 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.
-
公开(公告)号：US20220172705A1
公开(公告)日：2022-06-02
申请号：US17650452
申请日：2022-02-09
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 , 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.
-
Patent Agency Ranking
公开(公告)号：US12080272B2
公开(公告)日：2024-09-03
申请号：US17756264
申请日：2019-12-10
Applicant: Google LLC
Inventor： Robert Clark , Chun-an Chan , Vincent Wan
CPC classification number: G10L13/10 , G10L25/30 , G10L2013/105
Abstract: A method (400) for representing an intended prosody in synthesized speech includes receiving a text utterance (310) having at least one word (240), and selecting an utterance embedding (204) for the text utterance. Each word in the text utterance has at least one syllable (230) and each syllable has at least one phoneme (220). The utterance embedding represents an intended prosody. For each syllable, using the selected utterance embedding, the method also includes: predicting a duration (238) of the syllable by decoding a prosodic syllable embedding (232, 234) for the syllable based on attention by an attention mechanism (340) to linguistic features (222) of each phoneme of the syllable and generating a plurality of fixed-length predicted frames (260) based on the predicted duration for the syllable.
-
公开(公告)号：US11664011B2
公开(公告)日：2023-05-30
申请号：US17650452
申请日：2022-02-09
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 , G10L15/02 , G06N3/084 , G10L25/21 , G06N3/044 , G06N3/045
CPC classification number: G10L15/063 , G06N3/044 , G06N3/045 , G06N3/084 , G10L15/02 , G10L15/16 , G10L15/22 , G10L25/18 , G10L25/21 , G10L25/24 , G10L2015/025 , G10L2015/027
Abstract: A method of 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 has at least one syllable and each syllable has at least one phoneme. For each phoneme, the method further includes using the selected mel spectral embedding to: (i) predict a duration of the corresponding phoneme based on corresponding linguistic features associated with the word that includes the corresponding phoneme and corresponding linguistic features associated with the syllable that includes the corresponding phoneme; and (ii) generate 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 represents mel-spectral information of the corresponding phoneme.
-
公开(公告)号：US20230060886A1
公开(公告)日：2023-03-02
申请号：US18049995
申请日：2022-10-26
Applicant: Google LLC
Inventor： Robert Andrew James Clark , Chun-an Chan , Vincent Ping Leung Wan
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：US20220415306A1
公开(公告)日：2022-12-29
申请号：US17756264
申请日：2019-12-10
Applicant: Google LLC
Inventor： Robert Clark , Chun-an Chan , Vincent Wan
Abstract: A method (400) for representing an intended prosody in synthesized speech includes receiving a text utterance (310) having at least one word (240), and selecting an utterance embedding (204) for the text utterance. Each word in the text utterance has at least one syllable (230) and each syllable has at least one phoneme (220). The utterance embedding represents an intended prosody. For each syllable, using the selected utterance embedding, the method also includes: predicting a duration (238) of the syllable by decoding a prosodic syllable embedding (232, 234) for the syllable based on attention by an attention mechanism (340) to linguistic features (222) of each phoneme of the syllable and generating a plurality of fixed-length predicted frames (260) based on the predicted duration for the syllable.
-
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.
-
-
-
-
-
-
-
-
-
Search Results
16
records
(took 0.019 seconds)
