Showing eess.ASShow all
3 papers · 1 filter
eess.AS2025
MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition
Umberto Cappellazzo, Minsu Kim, Pingchuan Ma +4
Large language models (LLMs) have recently shown strong potential in audio-visual speech recognition (AVSR), but their high computational demands and sensitivity to token granulari…
eess.AS2025
Revival with Voice: Multi-modal Controllable Text-to-Speech Synthesis
Minsu Kim, Pingchuan Ma, Honglie Chen +2
This paper explores multi-modal controllable Text-to-Speech Synthesis (TTS) where the voice can be generated from face image, and the characteristics of output speech (e.g., pace,…
eess.AS2025
Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach
Umberto Cappellazzo, Minsu Kim, Stavros Petridis +2
Audio-Visual Speech Recognition (AVSR) enhances robustness in noisy environments by integrating visual cues. While recent advances integrate Large Language Models (LLMs) into AVSR,…