works on

From the 1 of 17 linked papers with an AI index.

activity
20242026
collaborators
Showing 2024Show all

5 papers · 1 filter

cs.SD2024

MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation

Shengkui Zhao, Yukun Ma, Chongjia Ni +7

Our previously proposed MossFormer has achieved promising performance in monaural speech separation. However, it predominantly adopts a self-attention-based MossFormer module, whic…

eess.AS2024

Speech Separation using Neural Audio Codecs with Embedding Loss

Jia Qi Yip, Chin Yuen Kwok, Bin Ma +1

Neural audio codecs have revolutionized audio processing by enabling speech tasks to be performed on highly compressed representations. Recent work has shown that speech separation…

cs.CL2024

Continual Learning Optimizations for Auto-regressive Decoder of Multilingual ASR systems

Chin Yuen Kwok, Jia Qi Yip, Eng Siong Chng

Continual Learning (CL) involves fine-tuning pre-trained models with new data while maintaining the performance on the pre-trained data. This is particularly relevant for expanding…

cs.SD2024

Towards Audio Codec-based Speech Separation

Jia Qi Yip, Shengkui Zhao, Dianwen Ng +2

Recent improvements in neural audio codec (NAC) models have generated interest in adopting pre-trained codecs for a variety of speech processing applications to take advantage of t…

eess.AS2024

Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis

Kun Zhou, Shengkui Zhao, Yukun Ma +7

Recent language model-based text-to-speech (TTS) frameworks demonstrate scalability and in-context learning capabilities. However, they suffer from robustness issues due to the acc…