5 papers
Hear, Invoke, and Understand: A Skill-Calling Multimodal Agent for Large Audio Language Models
Yuwen Wang, Tian-Hao Zhang, Minghao Cai +7
Complex acoustic problems may require models to perform acoustic operations, interact with external tools and reason over the resulting textual or processed-audio observations rath…
PALM-Bench: A Comprehensive Benchmark for Personalized Audio-Language Models
Yuwen Wang, Xinyuan Qian, Tian-Hao Zhang +6
Large Audio-Language Models (LALMs) have demonstrated strong performance in audio understanding and generation. Yet, our extensive benchmarking reveals that their behavior is large…
I2TTS: Image-indicated Immersive Text-to-speech Synthesis with Spatial Perception
Jiawei Zhang, Tian-Hao Zhang, Jun Wang +3
Controlling the style and characteristics of speech synthesis is crucial for adapting the output to specific contexts and user requirements. Previous Text-to-speech (TTS) works hav…
FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of Different Styles
Tian-Hao Zhang, Jiawei Zhang, Jun Wang +2
Humans can perceive speakers' characteristics (e.g., identity, gender, personality and emotion) by their appearance, which are generally aligned to their voice style. Recently, vis…
Breaking Through the Spike: Spike Window Decoding for Accelerated and Precise Automatic Speech Recognition
Wei Zhang, Tian-Hao Zhang, Chao Luo +4
Recently, end-to-end automatic speech recognition has become the mainstream approach in both industry and academia. To optimize system performance in specific scenarios, the Weight…