公开(公告)号：US11996116B2

公开(公告)日：2024-05-28

申请号：US17000583

申请日：2020-08-24

Applicant: Google LLC

Inventor： Joel Shor ,  Ronnie Maor ,  Oran Lang ,  Omry Tuval ,  Marco Tagliasacchi ,  Ira Shavitt ,  Felix de Chaumont Quitry ,  Dotan Emanuel ,  Aren Jansen

IPC: G10L25/30 ,  G06F18/21 ,  G06N3/084 ,  G06N3/088 ,  G06N5/046 ,  G10L25/48

CPC classification number: G10L25/30 ,  G06F18/217 ,  G06N3/084 ,  G06N3/088 ,  G06N5/046 ,  G10L25/48

Abstract: Examples relate to on-device non-semantic representation fine-tuning for speech classification. A computing system may obtain audio data having a speech portion and train a neural network to learn a non-semantic speech representation based on the speech portion of the audio data. The computing system may evaluate performance of the non-semantic speech representation based on a set of benchmark tasks corresponding to a speech domain and perform a fine-tuning process on the non-semantic speech representation based on one or more downstream tasks. The computing system may further generate a model based on the non-semantic representation and provide the model to a mobile computing device. The model is configured to operate locally on the mobile computing device.

公开(公告)号：US20220059117A1

公开(公告)日：2022-02-24

申请号：US17000583

申请日：2020-08-24

Applicant: Google LLC

Inventor： Joel Shor ,  Ronnie Maor ,  Oran Lang ,  Omry Tuval ,  Marco Tagliasacchi ,  Ira Shavitt ,  Felix de Chaumont Quitry ,  Dotan Emanuel ,  Aren Jansen

IPC: G10L25/30 ,  G10L25/48 ,  G06N3/08 ,  G06N5/04 ,  G06K9/62

Abstract: Examples relate to on-device non-semantic representation fine-tuning for speech classification. A computing system may obtain audio data having a speech portion and train a neural network to learn a non-semantic speech representation based on the speech portion of the audio data. The computing system may evaluate performance of the non-semantic speech representation based on a set of benchmark tasks corresponding to a speech domain and perform a fine-tuning process on the non-semantic speech representation based on one or more downstream tasks. The computing system may further generate a model based on the non-semantic representation and provide the model to a mobile computing device. The model is configured to operate locally on the mobile computing device.