Ziyang Ma

AudioTrust: Benchmarking The Multifaceted Trustworthiness of Audio Large Language Models

YuE: Scaling Open Foundation Models for Long-Form Music Generation

Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception

EmoPrefer: Can Large Language Models Understand Human Emotion Preferences?

Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Models

Audio-FLAN: An Instruction-Following Dataset for Unified Understanding and Generation of Speech, Music, and Sound

UltraVoice: Scaling Fine-Grained Style-Controlled Speech Conversations for Spoken Dialogue Models

Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis

MuPT: A Generative Symbolic Music Pretrained Transformer

F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement