no code implementations • 14 Sep 2023 • Lei Zhang, Zhengkun Tian, Xiang Chen, Jiaming Sun, Hongyu Xiang, Ke Ding, Guanglu Wan
To address this issue, we draw inspiration from the multifaceted capabilities of LLMs and Whisper, and focus on integrating multiple ASR text processing tasks related to speech recognition into the ASR model.
1 code implementation • 11 Nov 2022 • Jiangyan Yi, Chenglong Wang, JianHua Tao, Chu Yuan Zhang, Cunhang Fan, Zhengkun Tian, Haoxin Ma, Ruibo Fu
Some scene fake audio detection benchmark results on the SceneFake dataset are reported in this paper.
no code implementations • 7 Nov 2022 • Zhengkun Tian, Hongyu Xiang, Min Li, Feifei Lin, Ke Ding, Guanglu Wan
To reduce the peak latency, we propose a simple and novel method named peak-first regularization, which utilizes a frame-wise knowledge distillation function to force the probability distribution of the CTC model to shift left along the time axis instead of directly modifying the calculation process of CTC loss and gradients.
no code implementations • 20 Aug 2022 • Chenglong Wang, Jiangyan Yi, JianHua Tao, Haiyang Sun, Xun Chen, Zhengkun Tian, Haoxin Ma, Cunhang Fan, Ruibo Fu
The existing fake audio detection systems often rely on expert experience to design the acoustic features or manually design the hyperparameters of the network structure.
no code implementations • 17 Feb 2022 • Jiangyan Yi, Ruibo Fu, JianHua Tao, Shuai Nie, Haoxin Ma, Chenglong Wang, Tao Wang, Zhengkun Tian, Ye Bai, Cunhang Fan, Shan Liang, Shiming Wang, Shuai Zhang, Xinrui Yan, Le Xu, Zhengqi Wen, Haizhou Li, Zheng Lian, Bin Liu
Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021.
no code implementations • 28 Jan 2022 • Shuai Zhang, Jiangyan Yi, Zhengkun Tian, JianHua Tao, Yu Ting Yeung, Liqun Deng
We propose a language-related attention mechanism to reduce multilingual context confusion for the E2E code-switching ASR model based on the Equivalence Constraint (EC) Theory.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • ACL 2021 • Dianbo Sui, Zhengkun Tian, Yubo Chen, Kang Liu, Jun Zhao
In this paper, we aim to explore an uncharted territory, which is Chinese multimodal named entity recognition (NER) with both textual and acoustic contents.
no code implementations • 15 Apr 2021 • Haoxin Ma, Jiangyan Yi, JianHua Tao, Ye Bai, Zhengkun Tian, Chenglong Wang
However, fine-tuning leads to performance degradation on previous data.
1 code implementation • 8 Apr 2021 • Jiangyan Yi, Ye Bai, JianHua Tao, Haoxin Ma, Zhengkun Tian, Chenglong Wang, Tao Wang, Ruibo Fu
Therefore, this paper develops such a dataset for half-truth audio detection (HAD).
no code implementations • 7 Apr 2021 • Zhengkun Tian, Jiangyan Yi, Ye Bai, JianHua Tao, Shuai Zhang, Zhengqi Wen
It takes a lot of computation and time to predict the blank tokens, but only the non-blank tokens will appear in the final output sequence.
1 code implementation • 4 Apr 2021 • Zhengkun Tian, Jiangyan Yi, JianHua Tao, Ye Bai, Shuai Zhang, Zhengqi Wen, Xuefei Liu
To address these two problems, we propose a new model named the two-step non-autoregressive transformer(TSNAT), which improves the performance and accelerating the convergence of the NAR model by learning prior knowledge from a parameters-sharing AR model.
no code implementations • 15 Feb 2021 • Ye Bai, Jiangyan Yi, JianHua Tao, Zhengkun Tian, Zhengqi Wen, Shuai Zhang
Based on this idea, we propose a non-autoregressive speech recognition model called LASO (Listen Attentively, and Spell Once).
no code implementations • 9 Nov 2020 • Cunhang Fan, Jiangyan Yi, JianHua Tao, Zhengkun Tian, Bin Liu, Zhengqi Wen
The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 28 Oct 2020 • Zhengkun Tian, Jiangyan Yi, Ye Bai, JianHua Tao, Shuai Zhang, Zhengqi Wen
Inspired by the success of two-pass end-to-end models, we introduce a transformer decoder and the two-stage inference method into the streaming CTC model.
no code implementations • 28 Oct 2020 • Shuai Zhang, Jiangyan Yi, Zhengkun Tian, Ye Bai, JianHua Tao, Zhengqi Wen
In this paper, we propose a decoupled transformer model to use monolingual paired data and unpaired text data to alleviate the problem of code-switching data shortage.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • Pattern Recognition 2020 • Bocheng Zhao, JianHua Tao, Minghao Yang, Zhengkun Tian, Cunhang Fan, Ye Bai
Calligraphy imitation (CI) from a handful of target handwriting samples is such a challenging task that most of the existing writing style analysis or handwriting generation methods do not exhibit satisfactory performance.
no code implementations • 16 May 2020 • Zhengkun Tian, Jiangyan Yi, Jian-Hua Tao, Ye Bai, Shuai Zhang, Zhengqi Wen
To address this problem and improve the inference speed, we propose a spike-triggered non-autoregressive transformer model for end-to-end speech recognition, which introduces a CTC module to predict the length of the target sequence and accelerate the convergence.
no code implementations • 11 May 2020 • Ye Bai, Jiangyan Yi, Jian-Hua Tao, Zhengkun Tian, Zhengqi Wen, Shuai Zhang
Without beam-search, the one-pass propagation much reduces inference time cost of LASO.
no code implementations • 1 Apr 2020 • Jiangyan Yi, Jian-Hua Tao, Ye Bai, Zhengkun Tian, Cunhang Fan
The other is that POS tags are provided by an external POS tagger.
no code implementations • 19 Feb 2020 • Shuai Zhang, Jiangyan Yi, Zhengkun Tian, Jian-Hua Tao, Ye Bai
Recently, language identity information has been utilized to improve the performance of end-to-end code-switching (CS) speech recognition.
no code implementations • 6 Dec 2019 • Zhengkun Tian, Jiangyan Yi, Ye Bai, Jian-Hua Tao, Shuai Zhang, Zhengqi Wen
Once a fixed-length chunk of the input sequence is processed by the encoder, the decoder begins to predict symbols immediately.
no code implementations • 4 Dec 2019 • Ye Bai, Jiangyan Yi, Jian-Hua Tao, Zhengqi Wen, Zhengkun Tian, Shuai Zhang
To alleviate the above two issues, we propose a unified method called LST (Learn Spelling from Teachers) to integrate knowledge into an AED model from the external text-only data and leverage the whole context in a sentence.
no code implementations • 28 Sep 2019 • Zhengkun Tian, Jiangyan Yi, Jian-Hua Tao, Ye Bai, Zhengqi Wen
Furthermore, a path-aware regularization is proposed to assist SA-T to learn alignments and improve the performance.
no code implementations • 13 Jul 2019 • Ye Bai, Jiangyan Yi, Jian-Hua Tao, Zhengkun Tian, Zhengqi Wen
Integrating an external language model into a sequence-to-sequence speech recognition system is non-trivial.