7 papers
SimpleTool: Parallel Decoding for Real-Time LLM Function Calling
Xiaoxin Shi, Jiaxin Wan, Linkang Dong +3
LLM-based function calling enables intelligent agents to interact with external tools and environments, yet autoregressive decoding imposes a fundamental latency bottleneck that li…
T-Mimi: A Transformer-based Mimi Decoder for Real-Time On-Phone TTS
Haibin Wu, Bach Viet Do, Naveen Suda +10
Neural audio codecs provide promising acoustic features for speech synthesis, with representative streaming codecs like Mimi providing high-quality acoustic features for real-time…
Comprehend and Talk: Text to Speech Synthesis via Dual Language Modeling
Junjie Cao, Yichen Han, Ruonan Zhang +5
Existing Large Language Model (LLM) based autoregressive (AR) text-to-speech (TTS) systems, while achieving state-of-the-art quality, still face critical challenges. The foundation…
MBCodec:Thorough disentangle for high-fidelity audio compression
Ruonan Zhang, Xiaoyang Hao, Yichen Han +3
High-fidelity neural audio codecs in Text-to-speech (TTS) aim to compress speech signals into discrete representations for faithful reconstruction. However, prior approaches faced…
Quantize More, Lose Less: Autoregressive Generation from Residually Quantized Speech Representations
Yichen Han, Xiaoyang Hao, Keming Chen +25
Text-to-speech (TTS) synthesis has seen renewed progress under the discrete modeling paradigm. Existing autoregressive approaches often rely on single-codebook representations, whi…
Demystifying Adversarial Robustness in Diffusion Models: Compression, Randomness, and Geometry
Liu Yuezhang, Xue-Xin Wei
Recent studies suggest that diffusion models significantly improve the empirical adversarial robustness of deep neural network models. While intuitive explanations have been propos…