公开(公告)号：US20240194192A1

公开(公告)日：2024-06-13

申请号：US18078782

申请日：2022-12-09

Applicant: GOOGLE LLC

Inventor： Ehsan Amid ,  Rajiv Mathews ,  Shankar Kumar ,  Jared Lichtarge ,  Mingqing Chen ,  Tien-Ju Yang ,  Yuxin Ding

IPC: G10L15/16 ,  G10L15/06

CPC classification number: G10L15/16 ,  G10L15/063

Abstract: Information can be distilled from a global automatic speech recognition (ASR) model to a client ASR model. Many implementations include using an RNN-T model as the ASR model, where the global ASR model includes a global encoder, a joint network, a prediction network, and where the client ASR model includes a client encoder, the joint network, and the prediction network. Various implementations include using principal component analysis (PCA) while training the global ASR model to learn a mean vector and a set of principal components corresponding to the global ASR model. Additional or alternative implementations include training the client ASR model to generate one or more predicted coefficients of the global ASR model.

公开(公告)号：US20240371362A1

公开(公告)日：2024-11-07

申请号：US18652587

申请日：2024-05-01

Applicant: GOOGLE LLC

Inventor： Tien-Ju Yang ,  Yonghui Xiao ,  Giovanni Motta ,  Françoise Beaufays ,  Rajiv Mathews ,  Mingqing Chen

IPC: G10L15/06

Abstract: Implementations are directed to efficient federated learning of machine learning (ML) model(s) through on-the-fly decompression and compression of model parameters, of the ML model(s), when facilitating forward propagation and/or back propagation at client device(s). For example, implementations can transmit, from a remote system to a client device, a compressed on-device ML model that includes some compressed parameters. Further, the client device can, in performing forward propagation and/or back propagation using the on-device ML model, decompress those compressed parameters on-the-fly as the parameters are needed for the propagation. The propagation will utilize the decompressed parameters that were decompressed on the fly. Further, after the decompressed parameters are utilized, they can be deallocated from memory (while their compressed counterparts optionally remain in memory) to enable allocation of memory for further decompressed parameters that will be needed next and/or needed for other ongoing process(es).

公开(公告)号：US20240233707A9

公开(公告)日：2024-07-11

申请号：US18488578

申请日：2023-10-17

Applicant: Google LLC

Inventor： Tien-Ju Yang ,  You-Chi Cheng ,  Shankar Kumar ,  Jared Lichtarge ,  Ehsan Amid ,  Yuxin Ding ,  Rajiv Mathews ,  Mingqing Chen

IPC: G10L15/06 ,  G10L15/197 ,  G10L15/30

CPC classification number: G10L15/063 ,  G10L15/197 ,  G10L15/30 ,  G10L2015/0635

Abstract: A method includes receiving distillation data including a plurality of out-of-domain training utterances. For each particular out-of-domain training utterance of the distillation data, the method includes generating a corresponding augmented out-of-domain training utterance, and generating, using a teacher ASR model trained on training data corresponding to a target domain, a pseudo-label corresponding to the corresponding augmented out-of-domain training utterance. The method also includes distilling a student ASR model from the teacher ASR model by training the student ASR model using the corresponding augmented out-of-domain training utterances paired with the corresponding pseudo-labels generated by the teacher ASR model.

公开(公告)号：US20240135918A1

公开(公告)日：2024-04-25

申请号：US18488578

申请日：2023-10-16

Applicant: Google LLC

Inventor： Tien-Ju Yang ,  You-Chi Cheng ,  Shankar Kumar ,  Jared Lichtarge ,  Ehsan Amid ,  Yuxin Ding ,  Rajiv Mathews ,  Mingqing Chen

IPC: G10L15/06 ,  G10L15/197 ,  G10L15/30

CPC classification number: G10L15/063 ,  G10L15/197 ,  G10L15/30 ,  G10L2015/0635

Abstract: A method includes receiving distillation data including a plurality of out-of-domain training utterances. For each particular out-of-domain training utterance of the distillation data, the method includes generating a corresponding augmented out-of-domain training utterance, and generating, using a teacher ASR model trained on training data corresponding to a target domain, a pseudo-label corresponding to the corresponding augmented out-of-domain training utterance. The method also includes distilling a student ASR model from the teacher ASR model by training the student ASR model using the corresponding augmented out-of-domain training utterances paired with the corresponding pseudo-labels generated by the teacher ASR model.