-
公开(公告)号:US20240395239A1
公开(公告)日:2024-11-28
申请号:US18795734
申请日:2024-08-06
Applicant: Google LLC
Inventor: Daisy Antonia Stanton , Sean Matthew Shannon , Soroosh Mariooryad , Russell John Wyatt Skerry-Ryan , Eric Dean Battenberg , Thomas Edward Bagby , David Teh-Hwa Kao
IPC: G10L13/08 , G06N3/08 , G10L13/027
Abstract: Systems and methods for text-to-speech with novel speakers can obtain text data and output audio data. The input text data may be input along with one or more speaker preferences. The speaker preferences can include speaker characteristics. The speaker preferences can be processed by a machine-learned model conditioned on a learned prior distribution to determine a speaker embedding. The speaker embedding can then be processed with the text data to generate an output that includes audio data descriptive of the text data spoken by a novel speaker.
-
公开(公告)号:US20240386885A1
公开(公告)日:2024-11-21
申请号:US18662442
申请日:2024-05-13
Applicant: Google LLC
Inventor: Michelle Dana Tadmor , Eliya Nachmani , Alon Levkovitch , Julian Salazar , Chulayuth Asawaroengchai , Russell John Wyatt Skerry-Ryan , Soroosh Mariooryad
IPC: G10L15/183 , G10L13/027 , G10L15/02 , G10L15/06 , G10L25/18
Abstract: A method includes receiving an input sequence of speech features characterizing a spoken prompt. The method also includes generating a corresponding sequence of audio encodings using an audio encoder of a spoken language model. Without applying any intermediary cross-attention to the sequence of audio encoding between the audio encoder and a language model decoder of the spoken language model, the method includes processing the sequence of audio encodings generated by the audio encoder using the language model decoder to generate an output sequence of speech features characterizing a continuation of the spoken prompt.
-
公开(公告)号:US12067969B2
公开(公告)日:2024-08-20
申请号:US18302764
申请日:2023-04-18
Applicant: Google LLC
Inventor: Eric Dean Battenberg , Daisy Stanton , Russell John Wyatt Skerry-Ryan , Soroosh Mariooryad , David Teh-Hwa Kao , Thomas Edward Bagby , Sean Matthew Shannon
IPC: G10L13/00 , G10L13/047 , G10L13/10
CPC classification number: G10L13/047 , G10L13/10
Abstract: A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.
-
公开(公告)号:US20230206898A1
公开(公告)日:2023-06-29
申请号:US17673417
申请日:2022-02-16
Applicant: Google LLC
Inventor: Daisy Antonia Stanton , Sean Matthew Shannon , Soroosh Mariooryad , Russell John-Wyatt Skerry-Ryan , Eric Dean Battenberg , Thomas Edward Bagby , David Teh-Hwa Kao
IPC: G10L13/08 , G06N3/08 , G10L13/027
CPC classification number: G10L13/086 , G06N3/08 , G10L13/027
Abstract: Systems and methods for text-to-speech with novel speakers can obtain text data and output audio data. The input text data may be input along with one or more speaker preferences. The speaker preferences can include speaker characteristics. The speaker preferences can be processed by a machine-learned model conditioned on a learned prior distribution to determine a speaker embedding. The speaker embedding can then be processed with the text data to generate an output that includes audio data descriptive of the text data spoken by a novel speaker.
-
公开(公告)号:US11222621B2
公开(公告)日:2022-01-11
申请号:US16879714
申请日:2020-05-20
Applicant: Google LLC
Inventor: Eric Dean Battenberg , Daisy Stanton , Russell John Wyatt Skerry-Ryan , Soroosh Mariooryad , David Teh-hwa Kao , Thomas Edward Bagby , Sean Matthew Shannon
IPC: G10L15/22 , G06N3/00 , G06N3/08 , G10L13/047 , G10L13/10
Abstract: A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.
-
公开(公告)号:US20180101240A1
公开(公告)日:2018-04-12
申请号:US15783135
申请日:2017-10-13
Applicant: Google LLC
Inventor: Rodrigo Lima Carceroni , Pannag R. Sanketi , Suril Shah , Derya Ozkan , Soroosh Mariooryad , Seyed Mojtaba Seyedhosseini Tarzjani , Brett Lider , Peter Wilhelm Ludwig
CPC classification number: G06F3/017 , G04C3/002 , G06F1/163 , G06F1/1694 , G06F1/3215 , G06F1/3231 , G06F3/03 , G06F3/0482 , G06F3/0485 , G06F2200/1637 , H04M1/72569 , Y02D10/173
Abstract: An example method includes displaying, by a display (104) of a wearable device (100), a content card (114B); receiving, by the wearable device, motion data generated by a motion sensor (102) of the wearable device that represents motion of a forearm of a user of the wearable device; responsive to determining, based on the motion data, that the user has performed a movement that includes a supination of the forearm followed by a pronation of the forearm at an acceleration that is less than an acceleration of the supination, displaying, by the display, a next content card (114C); and responsive to determining, based on the motion data, that the user has performed a movement that includes a supination of the forearm followed by a pronation of the forearm at an acceleration that is greater than an acceleration of the supination, displaying, by the display, a previous content card (114A).
-
公开(公告)号:US20240395238A1
公开(公告)日:2024-11-28
申请号:US18796738
申请日:2024-08-07
Applicant: Google LLC
Inventor: Eric Dean Battenberg , Daisy Stanton , Russell John Wyatt Skerry-Ryan , Soroosh Mariooryad , David Teh-hwa Kao , Thomas Edward Bagby , Sean Matthew Shannon
IPC: G10L13/047 , G10L13/10
Abstract: A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.
-
公开(公告)号:US12087275B2
公开(公告)日:2024-09-10
申请号:US17673417
申请日:2022-02-16
Applicant: Google LLC
Inventor: Daisy Antonia Stanton , Sean Matthew Shannon , Soroosh Mariooryad , Russell John-Wyatt Skerry-Ryan , Eric Dean Battenberg , Thomas Edward Bagby , David Teh-Hwa Kao
IPC: G10L13/08 , G06N3/08 , G10L13/027
CPC classification number: G10L13/086 , G06N3/08 , G10L13/027
Abstract: Systems and methods for text-to-speech with novel speakers can obtain text data and output audio data. The input text data may be input along with one or more speaker preferences. The speaker preferences can include speaker characteristics. The speaker preferences can be processed by a machine-learned model conditioned on a learned prior distribution to determine a speaker embedding. The speaker embedding can then be processed with the text data to generate an output that includes audio data descriptive of the text data spoken by a novel speaker.
-
公开(公告)号:US11646010B2
公开(公告)日:2023-05-09
申请号:US17643455
申请日:2021-12-09
Applicant: Google LLC
Inventor: Eric Dean Battenberg , Daisy Stanton , Russell John Wyatt Skerry-Ryan , Soroosh Mariooryad , David Teh-Hwa Kao , Thomas Edward Bagby , Sean Matthew Shannon
IPC: G10L25/63 , G06F40/30 , G10L13/047 , G10L13/10
CPC classification number: G10L13/047 , G10L13/10
Abstract: A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.
-
公开(公告)号:US20220101826A1
公开(公告)日:2022-03-31
申请号:US17643455
申请日:2021-12-09
Applicant: Google LLC
Inventor: Eric Dean Battenberg , Daisy Stanton , Russell John Wyatt Skerry-Ryan , Soroosh Mariooryad , David Teh-Hwa Kao , Thomas Edward Bagby , Sean Matthew Shannon
IPC: G10L13/047 , G10L13/10
Abstract: A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.
-
-
-
-
-
-
-
-
-