65 citations · 78 across the 19 of their papers we have counts for
9 papers · 1 filter
Summary on the ISCSLP 2022 Chinese-English Code-Switching ASR Challenge
Shuhao Deng, Chengfei Li, Jinfeng Bai +6
Code-switching automatic speech recognition becomes one of the most challenging and the most valuable scenarios of automatic speech recognition, due to the code-switching phenomeno…
The Conversational Short-phrase Speaker Diarization (CSSD) Task: Dataset, Evaluation Metric and Baselines
Gaofeng Cheng, Yifan Chen, Runyan Yang +9
The conversation scenario is one of the most important and most challenging scenarios for speech processing technologies because people in conversation respond to each other in a c…
Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies
Zehan Li, Haoran Miao, Keqi Deng +4
There is often a trade-off between performance and latency in streaming automatic speech recognition (ASR). Traditional methods such as look-ahead and chunk-based methods, usually…
Interrelate Training and Searching: A Unified Online Clustering Framework for Speaker Diarization
Yifan Chen, Yifan Guo, Qingxuan Li +3
For online speaker diarization, samples arrive incrementally, and the overall distribution of the samples is invisible. Moreover, in most existing clustering-based methods, the tra…
Decoupled Federated Learning for ASR with Non-IID Data
Han Zhu, Jindong Wang, Gaofeng Cheng +2
Automatic speech recognition (ASR) with federated learning (FL) makes it possible to leverage data from multiple clients without compromising privacy. The quality of FL-based ASR c…
Boosting Cross-Domain Speech Recognition with Self-Supervision
Han Zhu, Gaofeng Cheng, Jindong Wang +3
The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions. Since the target domai…
Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset
Zehui Yang, Yifan Chen, Lei Luo +9
This paper introduces a high-quality rich annotated Mandarin conversational (RAMC) speech dataset called MagicData-RAMC. The MagicData-RAMC corpus contains 180 hours of conversatio…
Improving CTC-based speech recognition via knowledge transferring from pre-trained language models
Keqi Deng, Songjun Cao, Yike Zhang +4
Recently, end-to-end automatic speech recognition models based on connectionist temporal classification (CTC) have achieved impressive results, especially when fine-tuned from wav2…
Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models
Keqi Deng, Zehui Yang, Shinji Watanabe +3
While Transformers have achieved promising results in end-to-end (E2E) automatic speech recognition (ASR), their autoregressive (AR) structure becomes a bottleneck for speeding up…