公开(公告)号：US11538463B2

公开(公告)日：2022-12-27

申请号：US16383312

申请日：2019-04-12

Applicant: ADOBE INC.

Inventor： Trung Huu Bui ,  Subhadeep Dey ,  Franck Dernoncourt

IPC: G10L15/16 ,  G06N3/08 ,  G10L15/07

Abstract: Methods and systems are provided for generating a customized speech recognition neural network system comprised of an adapted automatic speech recognition neural network and an adapted language model neural network. The automatic speech recognition neural network is first trained in a generic domain and then adapted to a target domain. The language model neural network is first trained in a generic domain and then adapted to a target domain. Such a customized speech recognition neural network system can be used to understand input vocal commands.

公开(公告)号：US20200327884A1

公开(公告)日：2020-10-15

申请号：US16383312

申请日：2019-04-12

Applicant: ADOBE INC.

Inventor： Trung Huu Bui ,  Subhadeep Dey ,  Franck Dernoncourt

IPC: G10L15/16 ,  G10L15/07 ,  G06N3/08

Abstract: Methods and systems are provided for generating a customized speech recognition neural network system comprised of an adapted automatic speech recognition neural network and an adapted language model neural network. The automatic speech recognition neural network is first trained in a generic domain and then adapted to a target domain. The language model neural network is first trained in a generic domain and then adapted to a target domain. Such a customized speech recognition neural network system can be used to understand input vocal commands.

公开(公告)号：US12236975B2

公开(公告)日：2025-02-25

申请号：US17526810

申请日：2021-11-15

Applicant: Adobe Inc.

Inventor： Trung Bui ,  Subhadeep Dey ,  Seunghyun Yoon

IPC: G10L25/00 ,  G06F17/16 ,  G06F17/18 ,  G06N3/047 ,  G10L25/30 ,  G10L25/63

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for determining speech emotion. In particular, a speech emotion recognition system generates an audio feature vector and a textual feature vector for a sequence of words. Further, the speech emotion recognition system utilizes a neural attention mechanism that intelligently blends together the audio feature vector and the textual feature vector to generate attention output. Using the attention output, which includes consideration of both audio and text modalities for speech corresponding to the sequence of words, the speech emotion recognition system can apply attention methods to one of the feature vectors to generate a hidden feature vector. Based on the hidden feature vector, the speech emotion recognition system can generate a speech emotion probability distribution of emotions among a group of candidate emotions, and then select one of the candidate emotions as corresponding to the sequence of words.

公开(公告)号：US11205444B2

公开(公告)日：2021-12-21

申请号：US16543342

申请日：2019-08-16

Applicant: Adobe Inc.

Inventor： Trung Bui ,  Subhadeep Dey ,  Seunghyun Yoon

IPC: G10L25/00 ,  G10L25/63 ,  G06N3/04 ,  G06F17/18 ,  G06F17/16 ,  G10L25/30

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for determining speech emotion. In particular, a speech emotion recognition system generates an audio feature vector and a textual feature vector for a sequence of words. Further, the speech emotion recognition system utilizes a neural attention mechanism that intelligently blends together the audio feature vector and the textual feature vector to generate attention output. Using the attention output, which includes consideration of both audio and text modalities for speech corresponding to the sequence of words, the speech emotion recognition system can apply attention methods to one of the feature vectors to generate a hidden feature vector. Based on the hidden feature vector, the speech emotion recognition system can generate a speech emotion probability distribution of emotions among a group of candidate emotions, and then select one of the candidate emotions as corresponding to the sequence of words.

公开(公告)号：US20220076693A1

公开(公告)日：2022-03-10

申请号：US17526810

申请日：2021-11-15

Applicant: Adobe Inc.

Inventor： Trung Bui ,  Subhadeep Dey ,  Seunghyun Yoon

IPC: G10L25/63 ,  G06N3/04 ,  G06F17/18 ,  G06F17/16 ,  G10L25/30

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for determining speech emotion. In particular, a speech emotion recognition system generates an audio feature vector and a textual feature vector for a sequence of words. Further, the speech emotion recognition system utilizes a neural attention mechanism that intelligently blends together the audio feature vector and the textual feature vector to generate attention output. Using the attention output, which includes consideration of both audio and text modalities for speech corresponding to the sequence of words, the speech emotion recognition system can apply attention methods to one of the feature vectors to generate a hidden feature vector. Based on the hidden feature vector, the speech emotion recognition system can generate a speech emotion probability distribution of emotions among a group of candidate emotions, and then select one of the candidate emotions as corresponding to the sequence of words.

公开(公告)号：US20210050033A1

公开(公告)日：2021-02-18

申请号：US16543342

申请日：2019-08-16

Applicant: Adobe Inc.

Inventor： Trung Bui ,  Subhadeep Dey ,  Seunghyun Yoon

IPC: G10L25/63 ,  G06N3/04 ,  G10L25/30 ,  G06F17/16 ,  G06F17/18

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for determining speech emotion. In particular, a speech emotion recognition system generates an audio feature vector and a textual feature vector for a sequence of words. Further, the speech emotion recognition system utilizes a neural attention mechanism that intelligently blends together the audio feature vector and the textual feature vector to generate attention output. Using the attention output, which includes consideration of both audio and text modalities for speech corresponding to the sequence of words, the speech emotion recognition system can apply attention methods to one of the feature vectors to generate a hidden feature vector. Based on the hidden feature vector, the speech emotion recognition system can generate a speech emotion probability distribution of emotions among a group of candidate emotions, and then select one of the candidate emotions as corresponding to the sequence of words.