85 citations · 212 across the 22 of their papers we have counts for
22 papers
TST: Time-Sparse Transducer for Automatic Speech Recognition
Xiaohui Zhang, Mangui Liang, Zhengkun Tian +2
End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint an…
SceneFake: An Initial Dataset and Benchmarks for Scene Fake Audio Detection
Jiangyan Yi, Chenglong Wang, Jianhua Tao +5
Many datasets have been designed to further the development of fake audio detection. However, fake utterances in previous datasets are mostly generated by altering timbre, prosody,…
Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization
Zhengkun Tian, Hongyu Xiang, Min Li +3
The CTC model has been widely applied to many application scenarios because of its simple structure, excellent performance, and fast inference speed. There are many peaks in the pr…
Fully Automated End-to-End Fake Audio Detection
Chenglong Wang, Jiangyan Yi, Jianhua Tao +6
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. However,…
ADD 2022: the First Audio Deep Synthesis Detection Challenge
Jiangyan Yi, Ruibo Fu, Jianhua Tao +17
Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021. However, the recent shared tasks have not covered many real-life and challenging scenarios.…
Reducing language context confusion for end-to-end code-switching automatic speech recognition
Shuai Zhang, Jiangyan Yi, Zhengkun Tian +3
Code-switching deals with alternative languages in communication process. Training end-to-end (E2E) automatic speech recognition (ASR) systems for code-switching is especially chal…
Continual Learning for Fake Audio Detection
Haoxin Ma, Jiangyan Yi, Jianhua Tao +3
Fake audio attack becomes a major threat to the speaker verification system. Although current detection approaches have achieved promising results on dataset-specific scenarios, th…
FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization
Zhengkun Tian, Jiangyan Yi, Ye Bai +3
Transducer-based models, such as RNN-Transducer and transformer-transducer, have achieved great success in speech recognition. A typical transducer model decodes the output sequenc…
TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition
Zhengkun Tian, Jiangyan Yi, Jianhua Tao +4
The autoregressive (AR) models, such as attention-based encoder-decoder models and RNN-Transducer, have achieved great success in speech recognition. They predict the output sequen…
Half-Truth: A Partially Fake Audio Detection Dataset
Jiangyan Yi, Ye Bai, Jianhua Tao +5
Diverse promising datasets have been designed to hold back the development of fake audio detection, such as ASVspoof databases. However, previous datasets ignore an attacking situa…
Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT
Ye Bai, Jiangyan Yi, Jianhua Tao +3
Attention-based encoder-decoder (AED) models have achieved promising performance in speech recognition. However, because the decoder predicts text tokens (such as characters or wor…
Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognition
Cunhang Fan, Jiangyan Yi, Jianhua Tao +3
The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR). However,…
Decoupling Pronunciation and Language for End-to-end Code-switching Automatic Speech Recognition
Shuai Zhang, Jiangyan Yi, Zhengkun Tian +3
Despite the recent significant advances witnessed in end-to-end (E2E) ASR system for code-switching, hunger for audio-text paired data limits the further improvement of the models'…
One In A Hundred: Select The Best Predicted Sequence from Numerous Candidates for Streaming Speech Recognition
Zhengkun Tian, Jiangyan Yi, Ye Bai +3
The RNN-Transducers and improved attention-based encoder-decoder models are widely applied to streaming speech recognition. Compared with these two end-to-end models, the CTC model…
Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition
Zhengkun Tian, Jiangyan Yi, Jianhua Tao +3
Non-autoregressive transformer models have achieved extremely fast inference speed and comparable performance with autoregressive sequence-to-sequence models in neural machine tran…
Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition
Ye Bai, Jiangyan Yi, Jianhua Tao +3
Although attention based end-to-end models have achieved promising performance in speech recognition, the multi-pass forward computation in beam-search increases inference time cos…
Adversarial Transfer Learning for Punctuation Restoration
Jiangyan Yi, Jianhua Tao, Ye Bai +2
Previous studies demonstrate that word embeddings and part-of-speech (POS) tags are helpful for punctuation restoration tasks. However, two drawbacks still exist. One is that word…
Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition
Shuai Zhang, Jiangyan Yi, Zhengkun Tian +2
Recently, language identity information has been utilized to improve the performance of end-to-end code-switching (CS) speech recognition. However, previous works use an additional…
Synchronous Transformers for End-to-End Speech Recognition
Zhengkun Tian, Jiangyan Yi, Ye Bai +3
For most of the attention-based sequence-to-sequence models, the decoder predicts the output sequence conditioned on the entire input sequence processed by the encoder. The asynchr…
Integrating Knowledge into End-to-End Speech Recognition from External Text-Only Data
Ye Bai, Jiangyan Yi, Jianhua Tao +3
Attention-based encoder-decoder (AED) models have achieved promising performance in speech recognition. However, because of the end-to-end training, an AED model is usually trained…
Self-Attention Transducers for End-to-End Speech Recognition
Zhengkun Tian, Jiangyan Yi, Jianhua Tao +2
Recurrent neural network transducers (RNN-T) have been successfully applied in end-to-end speech recognition. However, the recurrent structure makes it difficult for parallelizatio…
Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition
Ye Bai, Jiangyan Yi, Jianhua Tao +2
Integrating an external language model into a sequence-to-sequence speech recognition system is non-trivial. Previous works utilize linear interpolation or a fusion network to inte…