18 citations · 46 across the 35 of their papers we have counts for
36 papers
LoOPSD: On-Policy Self-Distillation with Looped Teachers
Wei Fan, Qingyue Yang, Chao-Hong Tan +6
On-policy self-distillation improves a model using guidance from the model itself, but it still requires a teacher that provides more useful predictions than the student. Existing…
ConsensusBench: Benchmark of Consensus Nodes for LLM Reasoning via Outcome Reward Densifying
Shi-Qi Yan, Chao-Hong Tan, Qian Chen +3
Reinforcement learning (RL) has become one of the primary paradigms for reasoning enhancement of large language models (LLMs). In particular, Group Relative Policy Optimization (GR…
Short Horizons and Sparse Concepts: a Mathematical View of the Readout in the J-lens
Shi-Qi Yan, Kai-Xuan Ding, Chao-Hong Tan +4
The Jacobian lens (J-lens) has been proposed as a way to read verbalizable representations from language models. However, its principle and meaning lack a detailed and theoretical…
Efficient Chain-of-Modality Reasoning via Progressive Compression for Spoken Language Models
Pengchao Feng, Chao-Hong Tan, Qian Chen +3
Spoken language models (SLMs) enable natural human-computer interaction, but their reasoning ability still lags behind that of text-based large language models, especially on spoke…
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…
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…
WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training
Yifu Chen, Shengpeng Ji, Qian Chen +9
End-to-end spoken dialogue models have garnered significant attention because they offer a higher potential ceiling in expressiveness and perceptual ability than cascaded systems.…
Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models
Yifu Chen, Shengpeng Ji, Zhengqing Liu +6
Achieving seamless, human-like interaction remains a key challenge for full-duplex spoken dialogue models (SDMs). Reinforcement learning (RL) has substantially enhanced text- and v…
GenesisFunc: Multi-Agent Data Generation for Accurate and Generalizable Function-Calling
Hao-Xiang Xu, Chong Deng, Jiaqing Liu +5
Large Language Models (LLMs) extend their capabilities through function-calling (FC), which relies on training data with high quality, diversity, and broad coverage of scenario. Ho…
FGGM: Fisher-Guided Gradient Masking for Continual Learning
Chao-Hong Tan, Qian Chen, Wen Wang +6
Catastrophic forgetting impairs the continuous learning of large language models. We propose Fisher-Guided Gradient Masking (FGGM), a framework that mitigates this by strategically…
Say More with Less: Variable-Frame-Rate Speech Tokenization via Adaptive Clustering and Implicit Duration Coding
Rui-Chen Zheng, Wenrui Liu, Hui-Peng Du +6
Existing speech tokenizers typically assign a fixed number of tokens per second, regardless of the varying information density or temporal fluctuations in the speech signal. This u…
Pushing the Frontiers of Self-Distillation Prototypes Network with Dimension Regularization and Score Normalization
Yafeng Chen, Chong Deng, Hui Wang +4
Developing robust speaker verification (SV) systems without speaker labels has been a longstanding challenge. Earlier research has highlighted a considerable performance gap betwee…
OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation
Qinglin Zhang, Luyao Cheng, Chong Deng +8
Full-duplex spoken dialogue systems significantly surpass traditional turn-based dialogue systems, as they allow simultaneous bidirectional communication, closely mirroring human-h…
Unified Audio Event Detection
Yidi Jiang, Ruijie Tao, Wen Huang +2
Sound Event Detection (SED) detects regions of sound events, while Speaker Diarization (SD) segments speech conversations attributed to individual speakers. In SED, all speaker seg…
WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling
Shengpeng Ji, Ziyue Jiang, Wen Wang +14
Language models have been effectively applied to modeling natural signals, such as images, video, speech, and audio. A crucial component of these models is the codec tokenizer, whi…
Recording for Eyes, Not Echoing to Ears: Contextualized Spoken-to-Written Conversion of ASR Transcripts
Jiaqing Liu, Chong Deng, Qinglin Zhang +4
Automatic Speech Recognition (ASR) transcripts exhibit recognition errors and various spoken language phenomena such as disfluencies, ungrammatical sentences, and incomplete senten…
Multimodal Fusion and Coherence Modeling for Video Topic Segmentation
Hai Yu, Chong Deng, Qinglin Zhang +3
The video topic segmentation (VTS) task segments videos into intelligible, non-overlapping topics, facilitating efficient comprehension of video content and quick access to specifi…
FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs
Keyu An, Qian Chen, Chong Deng +30
This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions between humans and large language models (LLMs). At its core are two innovative mo…
Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision
Yafeng Chen, Siqi Zheng, Hui Wang +4
Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persisting challenge. In this paper, we propose a new self-supervi…
Skip-Layer Attention: Bridging Abstract and Detailed Dependencies in Transformers
Qian Chen, Wen Wang, Qinglin Zhang +7
The Transformer architecture has significantly advanced deep learning, particularly in natural language processing, by effectively managing long-range dependencies. However, as the…
Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token-based ASR
Qian Chen, Wen Wang, Qinglin Zhang +7
Recently, unified speech-text models, such as SpeechGPT, VioLA, and AudioPaLM, have achieved remarkable performance on various speech tasks. These models discretize speech signals…
CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation
Weixiang Yan, Yuchen Tian, Yunzhe Li +2
Recent code translation techniques exploit neural machine translation models to translate source code from one programming language to another to satisfy production compatibility o…
Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling
Hai Yu, Chong Deng, Qinglin Zhang +3
Topic segmentation is critical for obtaining structured documents and improving downstream tasks such as information retrieval. Due to its ability of automatically exploring clues…
LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT
Zhihao Du, Jiaming Wang, Qian Chen +12
Generative Pre-trained Transformer (GPT) models have achieved remarkable performance on various natural language processing tasks, and have shown great potential as backbones for a…