Lei Xie

This work presents a multimodal conversational-context framework for LLM-based ASR that integrates a scenario-controlled data pipeline, scalable multimodal context training, and systematic evaluation and introduces MM-ContextASR Bench, which evaluates contextual understanding and entity error correction across five scenarios.

A preference optimization framework with Large Audio-Language Model (LALM) feedback for controllable non-verbal vocalization (NVV) generation in continuous autoregressive speech models that enables DPO-style preference learning without explicit sequence likelihoods while preserving direct supervision on preferred realizations is proposed.

A lightweight Text Risk Score (TRS) is proposed, which estimates synthesis risk from interpretable text features without manual annotation or model training and shows a positive correlation with content errors and duration abnormalities, demonstrating its usefulness as a low-cost pre-synthesis indicator for complex-text risk diagnosis in low-resource multilingual TTS.

Systems that excel in dialect identification often leverage unique acoustic features, while ASR performance hinges on data normalization strategies.

FireRedAudio achieves state-of-the-art performance in audio understanding and generation by leveraging decoupled continuous representations, setting a new standard for unified audio-language models.

DiaScriber achieves unprecedented accuracy in multi-speaker scenarios, overcoming the challenges of overlapping speech and rapid transitions.

Dialect recognition in ASR can be significantly improved without sacrificing Mandarin accuracy, thanks to a novel self-distillation approach.

Real-world conversational dynamics significantly challenge target speaker extraction, revealing that even advanced systems struggle with natural overlap and noise.

Current spoken dialogue systems struggle with the nuances of human conversation, but a new benchmark offers a path to more natural interactions by focusing on handling interruptions and overlapping speech.