2 papers
cs.SD2023
Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy
Xulong Zhang, Haobin Tang, Jianzong Wang +3
Because of predicting all the target tokens in parallel, the non-autoregressive models greatly improve the decoding efficiency of speech recognition compared with traditional autor…
cs.SD2022
Tiny-Sepformer: A Tiny Time-Domain Transformer Network for Speech Separation
Jian Luo, Jianzong Wang, Ning Cheng +3
Time-domain Transformer neural networks have proven their superiority in speech separation tasks. However, these models usually have a large number of network parameters, thus ofte…