3 papers
eess.AS2026
FNH-TTS: Mixture-of-Experts Duration Modeling for Robust Neural Speech Synthesis
Qingliang Meng, Yuqing Deng, Wei Liang +3
Current non-autoregressive (NAR) text-to-speech (TTS) systems still struggle to model diverse and speaker-dependent duration variation. We further observe that richer duration vari…
cs.CL2025
ILT-Iterative LoRA Training through Focus-Feedback-Fix for Multilingual Speech Recognition
Qingliang Meng, Hao Wu, Wei Liang +2
The deep integration of large language models and automatic speech recognition systems has become a promising research direction with high practical value. To address the overfitti…
cs.CL2025
MTLM: Incorporating Bidirectional Text Information to Enhance Language Model Training in Speech Recognition Systems
Qingliang Meng, Pengju Ren, Tian Li +2
Automatic speech recognition (ASR) systems normally consist of an acoustic model (AM) and a language model (LM). The acoustic model estimates the probability distribution of text g…