Keqi Deng

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 26

Top Topics

Speech Recognition

Topic Hierarchies

Top Venues

IEEE ACM Trans. Audio Speech Lang. Process.

Publications

Keqi Deng, Philip C. Woodland
Decoupled structure for improved adaptability of end-to-end models. Speech Commun. 163 (2024)
Keqi Deng, Philip C. Woodland
Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation. ACL (1) (2024)
Keqi Deng, Guangzhi Sun, Philip C. Woodland
Wav2Prompt: End-to-End Speech Prompt Generation and Tuning For LLM in Zero and Few-shot Learning. CoRR (2024)
Keqi Deng, Philip C. Woodland
Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. 32 (2024)
Keqi Deng, Philip C. Woodland
FastInject: Injecting Unpaired Text Data into CTC-Based ASR Training. ICASSP (2024)
Keqi Deng, Philip C. Woodland
Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation. CoRR (2024)
Keqi Deng, Philip C. Woodland
Decoupled Structure for Improved Adaptability of End-to-End Models. CoRR (2023)
Keqi Deng, Philip C. Woodland
FastInject: Injecting Unpaired Text Data into CTC-based ASR training. CoRR (2023)
Keqi Deng, Philip C. Woodland
Adaptable End-to-End ASR Models Using Replaceable Internal LMs and Residual Softmax. ICASSP (2023)
Keqi Deng, Philip C. Woodland
Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax. CoRR (2023)
Keqi Deng, Songjun Cao, Yike Zhang, Long Ma, Gaofeng Cheng, Ji Xu, Pengyuan Zhang
Improving CTC-Based Speech Recognition Via Knowledge Transferring from Pre-Trained Language Models. ICASSP (2022)
Zehan Li, Haoran Miao, Keqi Deng, Gaofeng Cheng, Sanli Tian, Ta Li, Yonghong Yan
Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies. INTERSPEECH (2022)
Keqi Deng, Zehui Yang, Shinji Watanabe, Yosuke Higuchi, Gaofeng Cheng, Pengyuan Zhang
Improving Non-Autoregressive End-to-End Speech Recognition with Pre-Trained Acoustic and Language Models. ICASSP (2022)
Keqi Deng, Shinji Watanabe, Jiatong Shi, Siddhant Arora
Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation. INTERSPEECH (2022)
Keqi Deng, Shinji Watanabe, Jiatong Shi, Siddhant Arora
Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation. CoRR (2022)
Sanli Tian, Keqi Deng, Zehan Li, Lingxuan Ye, Gaofeng Cheng, Ta Li, Yonghong Yan
Knowledge Distillation For CTC-based Speech Recognition Via Consistent Acoustic Representation Learning. INTERSPEECH (2022)
Keqi Deng, Zehui Yang, Shinji Watanabe, Yosuke Higuchi, Gaofeng Cheng, Pengyuan Zhang
Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models. CoRR (2022)
Gaofeng Cheng, Haoran Miao, Runyan Yang, Keqi Deng, Yonghong Yan
ETEH: Unified Attention-Based End-to-End ASR and KWS Architecture. IEEE ACM Trans. Audio Speech Lang. Process. 30 (2022)
Keqi Deng, Gaofeng Cheng, Runyan Yang, Yonghong Yan
Alleviating ASR Long-Tailed Problem by Decoupling the Learning of Representation and Classification. IEEE ACM Trans. Audio Speech Lang. Process. 30 (2022)
Zehan Li, Haoran Miao, Keqi Deng, Gaofeng Cheng, Sanli Tian, Ta Li, Yonghong Yan
Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies. CoRR (2022)
Keqi Deng, Songjun Cao, Yike Zhang, Long Ma, Gaofeng Cheng, Ji Xu, Pengyuan Zhang
Improving CTC-based speech recognition via knowledge transferring from pre-trained language models. CoRR (2022)
Keqi Deng, Gaofeng Cheng, Haoran Miao, Pengyuan Zhang, Yonghong Yan
History Utterance Embedding Transformer LM for Speech Recognition. ICASSP (2021)
Keqi Deng, Songjun Cao, Long Ma
Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-Supervised Learning. Interspeech (2021)
Keqi Deng, Songjun Cao, Yike Zhang, Long Ma
Improving Hybrid CTC/Attention End-to-End Speech Recognition with Pretrained Acoustic and Language Models. ASRU (2021)
Keqi Deng, Songjun Cao, Yike Zhang, Long Ma
Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model. CoRR (2021)
Keqi Deng, Songjun Cao, Long Ma
Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-supervised Learning. CoRR (2021)