Xian-Gang Li

FunCineForge: A Unified Dataset Toolkit and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes

Movie dubbing is the task of synthesizing speech from scripts conditioned on video scenes, requiring accurate lip sync, faithful timbre transfer, and proper modeling of character identity and emotion. However, existing methods face two major limitations: (1) high-quality multimodal dubbing datasets are limited in scale...

The Platonic brain bridge hypothesis: human brain networks as an architectural prior for omni models

Qwen-Audio-Agent Technical Report

We present Qwen-Audio-Agent, a harness that combines full-duplex voice interaction with asynchronous task execution through a foreground-background architecture. A Frontend Agent manages dialogue and selects between direct tool use and delegation, while a Backend Agent carries out delegated tasks in a separate context....

agentic-ger: terminology recovery in long-form speech using global context

This work proposes Agentic-GER, an LLM-based agent for terminology correction in long-form speech, which uses global context from the full transcript to identify suspicious terms and resolve ambiguous hypotheses.

Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction

Real-time voice assistants must reason over evolving requests, execute actions, and follow conversational rules. Qwen-Audio-3.1-Realtime brings these requirements together through Think, Act, and Speak and Coordinate. Think combines Core-Cocktail supervised fine-tuning with Multimodality and Multi-Teacher On-Policy Dis...

The Evolving Bottleneck in Speech Generation: Interface Co-design and Staged Alignment from CosyVoice to Qwen-Audio-3.0-TTS

This technical retrospective offers a different account of the CosyVoice lineage, from CosyVoice through CosyVoice 2 and CosyVoice 3 to Qwen-Audio-3.0-TTS, and formalizes this history through four interface dimensions---representation, ownership, availability, and gradient reach---and separate within-paper evidence fro...

Multimodal Conversational Context for LLM-Based ASR: Data Construction, Training, and Benchmark

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 sce...

FunCineForge: A Unified Dataset Pipeline and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes

Movie dubbing is the task of synthesizing speech from scripts conditioned on video scenes, requiring accurate lip sync, faithful timbre transfer, and proper modeling of character identity and emotion. However, existing methods face two major limitations: (1) high-quality multimodal dubbing datasets are limited in scale...

TAG-Bench: Benchmarking Temporal Audio Grounding in Large Audio Language Models

Large audio language models (LALMs) can describe what is heard, but their ability to localize when queried content occurs remains less systematically evaluated. We present TAG-Bench, a benchmark for temporal audio grounding in which a model returns every time interval that matches a natural-language query. TAG-Bench co...

Semantic Refinement of Universal Audio Representations through Audio-Description Alignment

Universal audio representations must preserve acoustic detail while making high-level concepts accessible across speech, music, environmental sound, and downstream models of different capacities. We study semantic refinement of an acoustically pretrained encoder by adding audio-description alignment to a foundation of...

Qwen-Audio-3.0-Gen-Preview Technical Report

Qwen-Audio-3.0-Gen-Preview is presented, a unified non-autoregressive framework that uses a Diffusion Transformer and a shared variational autoencoder (VAE) to generate the complete mixed waveform and demonstrates the potential of unified generation for temporally structured audio without task-specific branches.

Listen, Do Not Copy: Internalizing Audio-Grounded Scaffold Context for Robust Omni-Model Speech Understanding

A joint GDPO task in which the model learns when to use a clue and how to produce a speaker-attributed transcript from separately normalized format, gate, and transcript rewards is formulated.