collaborators

5 papers

cs.SD2025

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…

cs.SD2025

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…

cs.SD2025

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…

cs.SD2025

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…

cs.SD2025

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…