Picture for Haihua Xu

Haihua Xu

Internal Language Model Estimation based Adaptive Language Model Fusion for Domain Adaptation

Nov 02, 2022
Figure 1 for Internal Language Model Estimation based Adaptive Language Model Fusion for Domain Adaptation
Figure 2 for Internal Language Model Estimation based Adaptive Language Model Fusion for Domain Adaptation
Figure 3 for Internal Language Model Estimation based Adaptive Language Model Fusion for Domain Adaptation
Figure 4 for Internal Language Model Estimation based Adaptive Language Model Fusion for Domain Adaptation
Viaarxiv icon

Speech-text based multi-modal training with bidirectional attention for improved speech recognition

Add code
Nov 01, 2022
Figure 1 for Speech-text based multi-modal training with bidirectional attention for improved speech recognition
Figure 2 for Speech-text based multi-modal training with bidirectional attention for improved speech recognition
Figure 3 for Speech-text based multi-modal training with bidirectional attention for improved speech recognition
Figure 4 for Speech-text based multi-modal training with bidirectional attention for improved speech recognition
Viaarxiv icon

Improving short-video speech recognition using random utterance concatenation

Oct 28, 2022
Figure 1 for Improving short-video speech recognition using random utterance concatenation
Figure 2 for Improving short-video speech recognition using random utterance concatenation
Figure 3 for Improving short-video speech recognition using random utterance concatenation
Figure 4 for Improving short-video speech recognition using random utterance concatenation
Viaarxiv icon

Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization

Add code
Oct 26, 2022
Figure 1 for Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization
Figure 2 for Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization
Figure 3 for Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization
Figure 4 for Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization
Viaarxiv icon

Intermediate-layer output Regularization for Attention-based Speech Recognition with Shared Decoder

Jul 09, 2022
Figure 1 for Intermediate-layer output Regularization for Attention-based Speech Recognition with Shared Decoder
Figure 2 for Intermediate-layer output Regularization for Attention-based Speech Recognition with Shared Decoder
Figure 3 for Intermediate-layer output Regularization for Attention-based Speech Recognition with Shared Decoder
Figure 4 for Intermediate-layer output Regularization for Attention-based Speech Recognition with Shared Decoder
Viaarxiv icon

Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognition

Jul 09, 2022
Figure 1 for Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognition
Figure 2 for Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognition
Figure 3 for Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognition
Figure 4 for Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognition
Viaarxiv icon

Internal language model estimation through explicit context vector learning for attention-based encoder-decoder ASR

Add code
Jan 26, 2022
Figure 1 for Internal language model estimation through explicit context vector learning for attention-based encoder-decoder ASR
Figure 2 for Internal language model estimation through explicit context vector learning for attention-based encoder-decoder ASR
Figure 3 for Internal language model estimation through explicit context vector learning for attention-based encoder-decoder ASR
Figure 4 for Internal language model estimation through explicit context vector learning for attention-based encoder-decoder ASR
Viaarxiv icon

Minimum word error training for non-autoregressive Transformer-based code-switching ASR

Oct 07, 2021
Figure 1 for Minimum word error training for non-autoregressive Transformer-based code-switching ASR
Figure 2 for Minimum word error training for non-autoregressive Transformer-based code-switching ASR
Figure 3 for Minimum word error training for non-autoregressive Transformer-based code-switching ASR
Figure 4 for Minimum word error training for non-autoregressive Transformer-based code-switching ASR
Viaarxiv icon

Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech

Add code
Jul 22, 2021
Figure 1 for Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
Figure 2 for Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
Figure 3 for Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
Figure 4 for Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
Viaarxiv icon

E2E-based Multi-task Learning Approach to Joint Speech and Accent Recognition

Jun 15, 2021
Figure 1 for E2E-based Multi-task Learning Approach to Joint Speech and Accent Recognition
Figure 2 for E2E-based Multi-task Learning Approach to Joint Speech and Accent Recognition
Figure 3 for E2E-based Multi-task Learning Approach to Joint Speech and Accent Recognition
Figure 4 for E2E-based Multi-task Learning Approach to Joint Speech and Accent Recognition
Viaarxiv icon