Alert button
Picture for Keqi Deng

Keqi Deng

Alert button

FastInject: Injecting Unpaired Text Data into CTC-based ASR training

Dec 14, 2023
Keqi Deng, Philip C. Woodland

Viaarxiv icon

Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition

Nov 19, 2023
Keqi Deng, Philip C. Woodland

Viaarxiv icon

Decoupled Structure for Improved Adaptability of End-to-End Models

Aug 25, 2023
Keqi Deng, Philip C. Woodland

Viaarxiv icon

Label-Synchronous Neural Transducer for End-to-End ASR

Jul 06, 2023
Keqi Deng, Philip C. Woodland

Figure 1 for Label-Synchronous Neural Transducer for End-to-End ASR
Figure 2 for Label-Synchronous Neural Transducer for End-to-End ASR
Figure 3 for Label-Synchronous Neural Transducer for End-to-End ASR
Figure 4 for Label-Synchronous Neural Transducer for End-to-End ASR
Viaarxiv icon

Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax

Feb 16, 2023
Keqi Deng, Philip C. Woodland

Figure 1 for Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax
Figure 2 for Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax
Figure 3 for Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax
Figure 4 for Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax
Viaarxiv icon

Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies

Jul 06, 2022
Zehan Li, Haoran Miao, Keqi Deng, Gaofeng Cheng, Sanli Tian, Ta Li, Yonghong Yan

Figure 1 for Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies
Figure 2 for Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies
Figure 3 for Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies
Viaarxiv icon

Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation

Apr 19, 2022
Keqi Deng, Shinji Watanabe, Jiatong Shi, Siddhant Arora

Figure 1 for Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation
Figure 2 for Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation
Figure 3 for Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation
Figure 4 for Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation
Viaarxiv icon

Improving CTC-based speech recognition via knowledge transferring from pre-trained language models

Feb 22, 2022
Keqi Deng, Songjun Cao, Yike Zhang, Long Ma, Gaofeng Cheng, Ji Xu, Pengyuan Zhang

Figure 1 for Improving CTC-based speech recognition via knowledge transferring from pre-trained language models
Figure 2 for Improving CTC-based speech recognition via knowledge transferring from pre-trained language models
Figure 3 for Improving CTC-based speech recognition via knowledge transferring from pre-trained language models
Figure 4 for Improving CTC-based speech recognition via knowledge transferring from pre-trained language models
Viaarxiv icon

Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models

Jan 26, 2022
Keqi Deng, Zehui Yang, Shinji Watanabe, Yosuke Higuchi, Gaofeng Cheng, Pengyuan Zhang

Figure 1 for Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models
Figure 2 for Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models
Figure 3 for Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models
Figure 4 for Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models
Viaarxiv icon