2.2k citations · 3.2k across the 79 of their papers we have counts for
21 papers · 1 filter
RefTAG: Reflection-aware Temporal Audio Grounding in Large Audio Language Models
Yuhang Dai, Xin Shu, Zhennan Lin +5
Temporal audio grounding requires locating every occurrence of a queried target, making both occurrence counts and interval boundaries essential. We propose RefTAG, a post-training…
The Evolving Bottleneck in Speech Generation: Interface Co-design and Staged Alignment from CosyVoice to Qwen-Audio-3.0-TTS
Qian Chen, Xiangang Li, Xiang Lv +2
Speech synthesis systems are commonly narrated as a sequence of larger models, better tokenizers, and broader data. This technical retrospective offers a different account of the C…
Semantic Refinement of Universal Audio Representations through Audio-Description Alignment
Lejun Min, Junyu Dai, Ruichen Zheng +7
Universal audio representations must preserve acoustic detail while making high-level concepts accessible across speech, music, environmental sound, and downstream models of differ…
TAG-Bench: Benchmarking Temporal Audio Grounding in Large Audio Language Models
Yuhang Dai, Xin Shu, Zengxi Li +3
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-Benc…
Beyond Reconstruction: Full-Context Generative DiT for Music Generation
Yunjia Li, Menglin Wu, Junyu Dai +13
Hybrid music generators combine the long-range planning of an autoregressive language model with the fidelity of a diffusion- or flow-based acoustic renderer. Yet renderers are tra…
Qwen-Audio-3.0-Gen-Preview Technical Report
Junyu Dai, Xiaoyue Duan, Xinyue Fan +14
Existing single-domain and multi-task audio systems remain limited in directly organizing heterogeneous audio components, ambience, and multiple roles into long-form temporal scene…
Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm
Bajian Xiang, Cheng Wen, Han Zhao +12
In this report, we present Qwen-Audio-3.0-TTS, a production-oriented speech synthesis system that jointly advances content consistency, speaker similarity, prosodic naturalness, au…
GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark
Yujie Tu, Yifan Yang, Tianrui Wang +35
While modern ASR systems achieve low error rates on high-resource benchmarks, such performance often overestimates real-world robustness. Existing evaluations address challenges in…
FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech
Haoxu Wang, Biao Tian, Weiqin Li +3
Existing Reinforcement Learning (RL) research for Text-to-Speech (TTS) focuses on large language models (LLMs), leaving Flow-Matching (FM) under-explored. We present FlowTTS-GRPO,…
AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation
Huadai Liu, Kaicheng Luo, Wen Wang +4
Unifying speech, sound, and music generation in one model is hindered by tradeoffs between fidelity, end-to-end training, in-context conditioning, and variable-length synthesis tha…
STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and Generation
Huadai Liu, Wen Wang, Kaicheng Luo +3
Continuous Variational Autoencoders (VAEs) serve as the fundamental continuous tokenizer for modern neural audio generation systems, enabling high-fidelity reconstruction while pro…
BareWave: Waveform-Native Flow-Matching Text-to-Speech
Wei Fan, Chao-Hong Tan, Qian Chen +5
Removing intermediate representations and separately trained decoding stages has become an important direction in generative modeling. In text-to-speech, however, high-quality syst…
FlowSE-GRPO: Training Flow Matching Speech Enhancement via Online Reinforcement Learning
Haoxu Wang, Biao Tian, Yiheng Jiang +5
Generative speech enhancement offers a promising alternative to traditional discriminative methods by modeling the distribution of clean speech conditioned on noisy inputs. Post-tr…
MELA-TTS: Joint transformer-diffusion model with representation alignment for speech synthesis
Keyu An, Zhiyu Zhang, Changfeng Gao +7
This work introduces MELA-TTS, a novel joint transformer-diffusion framework for end-to-end text-to-speech synthesis. By autoregressively generating continuous mel-spectrogram fram…
Audio Deep Fake Detection System with Neural Stitching for ADD 2022
Rui Yan, Cheng Wen, Shuran Zhou +3
This paper describes our best system and methodology for ADD 2022: The First Audio Deep Synthesis Detection Challenge\cite{Yi2022ADD}. The very same system was used for both two ro…
Time Domain Adversarial Voice Conversion for ADD 2022
Cheng Wen, Tingwei Guo, Xingjun Tan +5
In this paper, we describe our speech generation system for the first Audio Deep Synthesis Detection Challenge (ADD 2022). Firstly, we build an any-to-many voice conversion (VC) sy…
Semantic Data Augmentation for End-to-End Mandarin Speech Recognition
Jianwei Sun, Zhiyuan Tang, Hengxin Yin +6
End-to-end models have gradually become the preferred option for automatic speech recognition (ASR) applications. During the training of end-to-end ASR, data augmentation is a quit…
DiDiSpeech: A Large Scale Mandarin Speech Corpus
Tingwei Guo, Cheng Wen, Dongwei Jiang +8
This paper introduces a new open-sourced Mandarin speech corpus, called DiDiSpeech. It consists of about 800 hours of speech data at 48kHz sampling rate from 6000 speakers and the…
On Loss Functions and Recurrency Training for GAN-based Speech Enhancement Systems
Zhuohuang Zhang, Chengyun Deng, Yi Shen +5
Recent work has shown that it is feasible to use generative adversarial networks (GANs) for speech enhancement, however, these approaches have not been compared to state-of-the-art…
Transformer based unsupervised pre-training for acoustic representation learning
Ruixiong Zhang, Haiwei Wu, Wubo Li +3
Recently, a variety of acoustic tasks and related applications arised. For many acoustic tasks, the labeled data size may be limited. To handle this problem, we propose an unsuperv…
A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition
Dongwei Jiang, Wubo Li, Ruixiong Zhang +5
Building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, many unsupervised pre-training…