no code implementations • 12 Aug 2023 • Han Zhu, Dongji Gao, Gaofeng Cheng, Daniel Povey, Pengyuan Zhang, Yonghong Yan
Firstly, a generalized CTC loss function is introduced to handle noisy pseudo-labels by accepting alternative tokens in the positions of incorrect tokens.
no code implementations • 5 Jul 2023 • Haoran Miao, Gaofeng Cheng, Pengyuan Zhang, Yonghong Yan
However, how to deploy hybrid CTC/attention systems for online speech recognition is still a non-trivial problem.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 26 Feb 2023 • Changfeng Gao, Gaofeng Cheng, Pengyuan Zhang, Yonghong Yan
This study proposes a unsupervised target-aware data selection method based on speech corpora divergence (SCD), which can measure the similarity between two speech corpora.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 12 Oct 2022 • Shuhao Deng, Chengfei Li, Jinfeng Bai, Qingqing Zhang, Wei-Qiang Zhang, Runyan Yang, Gaofeng Cheng, Pengyuan Zhang, Yonghong Yan
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 phenomenon between multilingual language and the frequent occurrence of code-switching phenomenon in daily life.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 17 Aug 2022 • Gaofeng Cheng, Yifan Chen, Runyan Yang, Qingxuan Li, Zehui Yang, Lingxuan Ye, Pengyuan Zhang, Qingqing Zhang, Lei Xie, Yanmin Qian, Kong Aik Lee, Yonghong Yan
In the metric aspect, we design the new conversational DER (CDER) evaluation metric, which calculates the SD accuracy at the utterance level.
no code implementations • 6 Jul 2022 • Zehan Li, Haoran Miao, Keqi Deng, Gaofeng Cheng, Sanli Tian, Ta Li, Yonghong Yan
Firstly, we introduce a real-time encoder states revision strategy to modify previous states.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 28 Jun 2022 • Yifan Chen, Yifan Guo, Qingxuan Li, Gaofeng Cheng, Pengyuan Zhang, Yonghong Yan
For online speaker diarization, samples arrive incrementally, and the overall distribution of the samples is invisible.
1 code implementation • 20 Jun 2022 • Han Zhu, Gaofeng Cheng, Jindong Wang, Wenxin Hou, Pengyuan Zhang, Yonghong Yan
The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • 18 Jun 2022 • Han Zhu, Jindong Wang, Gaofeng Cheng, Pengyuan Zhang, Yonghong Yan
Secondly, to reduce the communication and computation costs, we propose decoupled federated learning (DecoupleFL).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 31 Mar 2022 • Zehui Yang, Yifan Chen, Lei Luo, Runyan Yang, Lingxuan Ye, Gaofeng Cheng, Ji Xu, Yaohui Jin, Qingqing Zhang, Pengyuan Zhang, Lei Xie, Yonghong Yan
As a Mandarin speech dataset designed for dialog scenarios with high quality and rich annotations, MagicData-RAMC enriches the data diversity in the Mandarin speech community and allows extensive research on a series of speech-related tasks, including automatic speech recognition, speaker diarization, topic detection, keyword search, text-to-speech, etc.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
1 code implementation • 22 Feb 2022 • Keqi Deng, Songjun Cao, Yike Zhang, Long Ma, Gaofeng Cheng, Ji Xu, Pengyuan Zhang
Recently, end-to-end automatic speech recognition models based on connectionist temporal classification (CTC) have achieved impressive results, especially when fine-tuned from wav2vec2. 0 models.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • 25 Jan 2022 • Keqi Deng, Zehui Yang, Shinji Watanabe, Yosuke Higuchi, Gaofeng Cheng, Pengyuan Zhang
The proposed NAR model significantly surpasses previous NAR systems on the AISHELL-1 benchmark and shows a potential for English tasks.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 23 Dec 2021 • Changfeng Gao, Gaofeng Cheng, Pengyuan Zhang
Nevertheless, most of the previous SSL methods ignore the influence of the background noise or reverberation, which is crucial to deploying ASR systems in real-world speech applications.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • 9 Oct 2021 • Han Zhu, Li Wang, Jindong Wang, Gaofeng Cheng, Pengyuan Zhang, Yonghong Yan
In this work, in order to build a better pre-trained model for low-resource ASR, we propose a pre-training approach called wav2vec-S, where we use task-specific semi-supervised pre-training to refine the self-supervised pre-trained model for the ASR task thus more effectively utilize the capacity of the pre-trained model to generate task-specific representations for ASR.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 15 Jan 2020 • Haoran Miao, Gaofeng Cheng, Changfeng Gao, Pengyuan Zhang, Yonghong Yan
To support the online recognition, we integrate the state reuse chunk-SAE and the MTA based SAD into online CTC/attention architecture.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 25 Dec 2019 • Lu Huang, Gaofeng Cheng, Pengyuan Zhang, Yi Yang, Shumin Xu, Jiasong Sun
The experimental results show that uPIT outperforms cPIT when LC-BLSTM is used during inference.
1 code implementation • Interspeech 2018 2018 • Daniel Povey, Gaofeng Cheng, Yiming Wang, Ke Li, Hainan Xu, Mahsa Yarmohammadi, Sanjeev Khudanpur
Time Delay Neural Networks (TDNNs), also known as onedimensional Convolutional Neural Networks (1-d CNNs), are an efficient and well-performing neural network architecture for speech recognition.