5 papers
GLM-TTS Technical Report
Jiayan Cui, Zhihan Yang, Naihan Li +10
This work proposes GLM-TTS, a production-level TTS system designed for efficiency, controllability, and high-fidelity speech generation. GLM-TTS follows a two-stage architecture, c…
A Fast and Lightweight Model for Causal Audio-Visual Speech Separation
Wendi Sang, Kai Li, Runxuan Yang +2
Audio-visual speech separation (AVSS) aims to extract a target speech signal from a mixed signal by leveraging both auditory and visual (lip movement) cues. However, most existing…
Enhancing Spectrogram Realism in Singing Voice Synthesis via Explicit Bandwidth Extension Prior to Vocoder
Runxuan Yang, Kai Li, Guo Chen +1
This paper addresses the challenge of enhancing the realism of vocoder-generated singing voice audio by mitigating the distinguishable disparities between synthetic and real-life r…
Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation
Guo Chen, Kai Li, Runxuan Yang +1
Existing causal speech separation models often underperform compared to non-causal models due to difficulties in retaining historical information. To address this, we propose the T…
SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios
Kai Li, Wendi Sang, Chang Zeng +3
Systematic evaluation of speech separation and enhancement models under moving sound source conditions requires extensive and diverse data. However, real-world datasets often lack…