ASR

EfficientASR: Speech Recognition Network Compression via Attention Redundancy and Chunk-Level FFN Optimization
In recent years, Transformer networks have shown remarkable performance in speech recognition tasks. However, their deployment poses …
Cite arXiv
EfficientASR: Speech Recognition Network Compression via Attention Redundancy and Chunk-Level FFN Optimization
Boosting Chinese ASR Error Correction with Dynamic Error Scaling Mechanism
Chinese Automatic Speech Recognition (ASR) error correction presents significant challenges due to the Chinese language’s unique …
PDF Cite arXiv ISCA
Boosting Chinese ASR Error Correction with Dynamic Error Scaling Mechanism
Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy
Because of predicting all the target tokens in parallel, the non-autoregressive models greatly improve the decoding efficiency of …
Cite arXiv IEEE
Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy
Improving Speech Representation Learning via Speech-level and Phoneme-level Masking Approach
Recovering the masked speech frames is widely applied in speech representation learning. However, most of these models use random …
Cite arXiv IEEE
Improving Speech Representation Learning via Speech-level and Phoneme-level Masking Approach
Linguistic-Enhanced Transformer with CTC Embedding for Speech Recognition
The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement …
Cite arXiv IEEE
Linguistic-Enhanced Transformer with CTC Embedding for Speech Recognition
Adaptive Activation Network for Low Resource Multilingual Speech Recognition
Low resource automatic speech recognition (ASR) is a useful but thorny task, since deep learning ASR models usually need huge amounts …
Cite arXiv IEEE
Adaptive Activation Network for Low Resource Multilingual Speech Recognition
Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition
The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline …
Cite arXiv IEEE
A Language Model Based Pseudo-Sample Deliberation for Semi-supervised Speech Recognition
End-to-end modeling requires tremendous amounts of transcribed speech to achieve an automatic speech recognition (ASR) model with high …
Cite IEEE
A Language Model Based Pseudo-Sample Deliberation for Semi-supervised Speech Recognition
CACnet: Cube Attentional CNN for Automatic Speech Recognition
End-to-end models have been widely used in Automatic Speech Recognition (ASR). Convolutional Neural Networks (CNNs) can effectively use …
Cite IEEE
CACnet: Cube Attentional CNN for Automatic Speech Recognition
Loss Prediction: End-to-End Active Learning Approach For Speech Recognition
End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is …
Cite arXiv IEEE
Loss Prediction: End-to-End Active Learning Approach For Speech Recognition