2.2k citations · 3.2k across the 79 of their papers we have counts for
15 papers · 1 filter
Qwen-Audio-3.1-ASR Technical Report
Chuanmeng Bian, Daren Chen, Peixin Chen +45
We present Qwen-Audio-3.1-ASR, a family of audio-language models that builds upon its predecesor Qwen-Audio-3.0-ASR with improved speech recognition and expanded capabilities in sp…
Qwen-Audio-Jev: A Unified Interface for Audio Decisions
Peixin Chen, Ying Fang, Zhifu Gao +19
Large audio language models (LALMs) have made substantial progress in audio understanding. However, autoregressive text generation introduces computational overhead and latency in…
Listen, Do Not Copy: Internalizing Audio-Grounded Scaffold Context for Robust Omni-Model Speech Understanding
Pengfei Zhang, Biao Tian, Tianxin Xie +3
Omni models transcribe clean, single-speaker speech well, but their accuracy drops sharply when speakers overlap and the scene is noisy, exactly where knowing who said what matters…
Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering
Junyu Dai, Xinyue Fan, Weiqin Li +14
In this report, we present a unified song generation framework capable of producing high-quality full-length music from lyrics, text descriptions, and musical attributes. The propo…
TF-MossFormer: Integrating Convolution Gated Local-Global Attentions for Enhanced Time-Frequency Domain Monaural Speech Separation
Shengkui Zhao, Zexu Pan, Haoxu Wang +3
Transformers with global attention capture long-range dependencies but can miss the fine-grained local continuity crucial for speech separation. We propose TF-MossFormer, a time-fr…
UniVocal: Unified Speech-Singing Code-Switching Synthesis
Yufei Shi, Qian Chen, Wen Wang +3
We propose UniVocal, a unified framework that implicitly infers vocal modes from text context to pioneer Speech-Singing Code-Switching (SCS) Synthesis - a task where transitions ar…
E2E-AEC: Implementing an end-to-end neural network learning approach for acoustic echo cancellation
Yiheng Jiang, Biao Tian, Haoxu Wang +4
We propose a novel neural network-based end-to-end acoustic echo cancellation (E2E-AEC) method capable of streaming inference, which operates effectively without reliance on tradit…
RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS
Cong Wang, Changfeng Gao, Yang Xiang +7
Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward hacking, particularl…
PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation
Huadai Liu, Kaicheng Luo, Wen Wang +6
Video-to-Audio (V2A) generation requires balancing four critical perceptual dimensions: semantic consistency, audio-visual temporal synchrony, aesthetic quality, and spatial accura…
Explore the Reinforcement Learning for the LLM based ASR and TTS system
Changfeng Gao, Yabin Li, Keyu An +4
In recent years, large language models (LLMs) have played an important role in automatic speech recognition (ASR) and text-to-speech (TTS) systems. While reinforcement learning (RL…
Eliminating stability hallucinations in llm-based tts models via attention guidance
ShiMing Wang, ZhiHao Du, Yang Xiang +6
This paper focuses on resolving stability hallucinations (e.g., repetitive or omitted speech) in LLM-based Text-to-Speech (TTS) models by improving and leveraging the attention mec…
SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Models
Han Yin, Yafeng Chen, Chong Deng +6
The Speaker Diarization and Recognition (SDR) task aims to predict "who spoke when and what" within an audio clip, which is a crucial task in various real-world multi-speaker scena…
Audio-Visual Wake Word Spotting System For MISP Challenge 2021
Yanguang Xu, Jianwei Sun, Yang Han +7
This paper presents the details of our system designed for the Task 1 of Multimodal Information Based Speech Processing (MISP) Challenge 2021. The purpose of Task 1 is to leverage…
GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
Guoguo Chen, Shuzhou Chai, Guanbo Wang +18
This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and…
Cross-task pre-training for on-device acoustic scene classification
Ruixiong Zhang, Wei Zou, Xiangang Li
Acoustic scene classification (ASC) and acoustic event detection (AED) are different but related tasks. Acoustic events can provide useful information for recognizing acoustic scen…