-
公开(公告)号：US20230130634A1
公开(公告)日：2023-04-27
申请号：US17936547
申请日：2022-09-29
Applicant: Google LLC
Inventor： Tara N. Sainath , Rami Botros , Anmol Gulati , Krzysztof Choromanski , Ruoming Pang , Trevor Strohman , Weiran Wang , Jiahui Yu
Abstract: A computer-implemented method includes receiving a sequence of acoustic frames as input to an automatic speech recognition (ASR) model. Here, the ASR model includes a causal encoder and a decoder. The method also includes generating, by the causal encoder, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The method also includes generating, by the decoder, a first probability distribution over possible speech recognition hypotheses. Here, the causal encoder includes a stack of causal encoder layers each including a Recurrent Neural Network (RNN) Attention-Performer module that applies linear attention.
-
公开(公告)号：US20220310071A1
公开(公告)日：2022-09-29
申请号：US17330446
申请日：2021-05-26
Applicant: Google LLC
Inventor： Rami Botros , Tara Sainath
Abstract: A RNN-T model includes a prediction network configured to, at each of a plurality of times steps subsequent to an initial time step, receive a sequence of non-blank symbols. For each non-blank symbol the prediction network is also configured to generate, using a shared embedding matrix, an embedding of the corresponding non-blank symbol, assign a respective position vector to the corresponding non-blank symbol, and weight the embedding proportional to a similarity between the embedding and the respective position vector. The prediction network is also configured to generate a single embedding vector at the corresponding time step. The RNN-T model also includes a joint network configured to, at each of the plurality of time steps subsequent to the initial time step, receive the single embedding vector generated as output from the prediction network at the corresponding time step and generate a probability distribution over possible speech recognition hypotheses.
-
公开(公告)号：US11727920B2
公开(公告)日：2023-08-15
申请号：US17330446
申请日：2021-05-26
Applicant: Google LLC
Inventor： Rami Botros , Tara Sainath
CPC classification number: G10L15/16 , G10L15/083
Abstract: A RNN-T model includes a prediction network configured to, at each of a plurality of times steps subsequent to an initial time step, receive a sequence of non-blank symbols. For each non-blank symbol the prediction network is also configured to generate, using a shared embedding matrix, an embedding of the corresponding non-blank symbol, assign a respective position vector to the corresponding non-blank symbol, and weight the embedding proportional to a similarity between the embedding and the respective position vector. The prediction network is also configured to generate a single embedding vector at the corresponding time step. The RNN-T model also includes a joint network configured to, at each of the plurality of time steps subsequent to the initial time step, receive the single embedding vector generated as output from the prediction network at the corresponding time step and generate a probability distribution over possible speech recognition hypotheses.
-
公开(公告)号：US11715458B2
公开(公告)日：2023-08-01
申请号：US17316198
申请日：2021-05-10
Applicant: Google LLC
Inventor： Tara Sainath , Arun Narayanan , Rami Botros , Yanzhang He , Ehsan Variani , Cyril Allauzen , David Rybach , Ruoming Pang , Trevor Strohman
CPC classification number: G10L15/063 , G10L15/02 , G10L15/22 , G10L15/30
Abstract: An ASR model includes a first encoder configured to receive a sequence of acoustic frames and generate a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The ASR model also includes a second encoder configured to receive the first higher order feature representation generated by the first encoder at each of the plurality of output steps and generate a second higher order feature representation for a corresponding first higher order feature frame. The ASR model also includes a decoder configured to receive the second higher order feature representation generated by the second encoder at each of the plurality of output steps and generate a first probability distribution over possible speech recognition hypothesis. The ASR model also includes a language model configured to receive the first probability distribution over possible speech hypothesis and generate a rescored probability distribution.
-
公开(公告)号：US20240379094A1
公开(公告)日：2024-11-14
申请号：US18779894
申请日：2024-07-22
Applicant: Google LLC
Inventor： Rami Botros , Tara Sainath
Abstract: A RNN-T model includes a prediction network configured to, at each of a plurality of times steps subsequent to an initial time step, receive a sequence of non-blank symbols. For each non-blank symbol the prediction network is also configured to generate, using a shared embedding matrix, an embedding of the corresponding non-blank symbol, assign a respective position vector to the corresponding non-blank symbol, and weight the embedding proportional to a similarity between the embedding and the respective position vector. The prediction network is also configured to generate a single embedding vector at the corresponding time step. The RNN-T model also includes a joint network configured to, at each of the plurality of time steps subsequent to the initial time step, receive the single embedding vector generated as output from the prediction network at the corresponding time step and generate a probability distribution over possible speech recognition hypotheses.
-
Patent Agency Ranking
公开(公告)号：US12062363B2
公开(公告)日：2024-08-13
申请号：US18347842
申请日：2023-07-06
Applicant: Google LLC
Inventor： Rami Botros , Tara Sainath
CPC classification number: G10L15/16 , G10L15/083
Abstract: A recurrent neural network-transducer (RNN-T) model improves speech recognition by processing sequential non-blank symbols at each time step after an initial one. The model's prediction network receives a sequence of symbols from a final Softmax layer and employs a shared embedding matrix to create and map embeddings to each symbol, associating them with unique position vectors. These embeddings are weighted according to their similarity to their matching position vector. Subsequently, a joint network of the RNN-T model uses these weighted embeddings to output a probability distribution for potential speech recognition hypotheses at each time step, enabling more accurate transcriptions of spoken language.
-
公开(公告)号：US20230343328A1
公开(公告)日：2023-10-26
申请号：US18336211
申请日：2023-06-16
Applicant: Google LLC
Inventor： Tara Sainath , Arun Narayanan , Rami Botros , Yanzhang He , Ehsan Variani , Cyril Allauzen , David Rybach , Ruoming Pang , Trevor Strohman
CPC classification number: G10L15/063 , G10L15/02 , G10L15/22 , G10L15/30
Abstract: An ASR model includes a first encoder configured to receive a sequence of acoustic frames and generate a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The ASR model also includes a second encoder configured to receive the first higher order feature representation generated by the first encoder at each of the plurality of output steps and generate a second higher order feature representation for a corresponding first higher order feature frame. The ASR model also includes a decoder configured to receive the second higher order feature representation generated by the second encoder at each of the plurality of output steps and generate a first probability distribution over possible speech recognition hypothesis. The ASR model also includes a language model configured to receive the first probability distribution over possible speech hypothesis and generate a rescored probability distribution.
-
公开(公告)号：US20230326461A1
公开(公告)日：2023-10-12
申请号：US18182925
申请日：2023-03-13
Applicant: Google LLC
Inventor： Shaojin Ding , Yangzhang He , Xin Wang , Weiran Wang , Trevor Strohman , Tara N. Sainath , Rohit Parkash Prabhavalkar , Robert David , Rina Panigrahy , Rami Botros , Qiao Liang , Ian Mcgraw , Ding Zhao , Dongseong Hwang
CPC classification number: G10L15/32 , G10L15/16 , G10L15/22 , G10L2015/223
Abstract: An automated speech recognition (ASR) model includes a first encoder, a first encoder, a second encoder, and a second decoder. The first encoder receives, as input, a sequence of acoustic frames, and generates, at each of a plurality of output steps, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The first decoder receives, as input, the first higher order feature representation generated by the first encoder, and generates a first probability distribution over possible speech recognition hypotheses. The second encoder receives, as input, the first higher order feature representation generated by the first encoder, and generates a second higher order feature representation for a corresponding first higher order feature frame. The second decoder receives, as input, the second higher order feature representation generated by the second encoder, and generates a second probability distribution over possible speech recognition hypotheses.
-
公开(公告)号：US12190869B2
公开(公告)日：2025-01-07
申请号：US17936547
申请日：2022-09-29
Applicant: Google LLC
Inventor： Tara N. Sainath , Rami Botros , Anmol Gulati , Krzysztof Choromanski , Ruoming Pang , Trevor Strohman , Weiran Wang , Jiahui Yu
Abstract: A computer-implemented method includes receiving a sequence of acoustic frames as input to an automatic speech recognition (ASR) model. Here, the ASR model includes a causal encoder and a decoder. The method also includes generating, by the causal encoder, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The method also includes generating, by the decoder, a first probability distribution over possible speech recognition hypotheses. Here, the causal encoder includes a stack of causal encoder layers each including a Recurrent Neural Network (RNN) Attention-Performer module that applies linear attention.
-
公开(公告)号：US20240371363A1
公开(公告)日：2024-11-07
申请号：US18772263
申请日：2024-07-15
Applicant: Google LLC
Inventor： Tara Sainath , Arun Narayanan , Rami Botros , Yanzhang He , Ehsan Variani , Cyril Allauzen , David Rybach , Ruoming Pang , Trevor Strohman
Abstract: An ASR model includes a first encoder configured to receive a sequence of acoustic frames and generate a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The ASR model also includes a second encoder configured to receive the first higher order feature representation generated by the first encoder at each of the plurality of output steps and generate a second higher order feature representation for a corresponding first higher order feature frame. The ASR model also includes a decoder configured to receive the second higher order feature representation generated by the second encoder at each of the plurality of output steps and generate a first probability distribution over possible speech recognition hypothesis. The ASR model also includes a language model configured to receive the first probability distribution over possible speech hypothesis and generate a rescored probability distribution.
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.068 seconds)
