5 papers
Bridging What the Model Thinks and How It Speaks: Expressive Speech Generation via Self-Aware Intent-Realization Alignment
Kuang Wang, Lai Wei, Ping Lin +8
Speech Language Models (SLMs) exhibit strong semantic understanding, yet often fail to translate this capacity into expressive acoustic realization, producing speech with flattened…
Workflow is All You Need: Escaping the "Statistical Smoothing Trap" via High-Entropy Information Foraging and Adversarial Pacing
Zhongjie Jiang
Central to long-form text generation in vertical domains is the "impossible trinity" confronting current large language models (LLMs): the simultaneous achievement of low hallucina…
The Necessity of Imperfection:Reversing Model Collapse via Simulating Cognitive Boundedness
Zhongjie Jiang
Although synthetic data is widely promoted as a remedy, its prevailing production paradigm -- one optimizing for statistical smoothness -- systematically removes the long-tail, cog…
Accent Normalization Using Self-Supervised Discrete Tokens with Non-Parallel Data
Qibing Bai, Sho Inoue, Shuai Wang +3
Accent normalization converts foreign-accented speech into native-like speech while preserving speaker identity. We propose a novel pipeline using self-supervised discrete tokens a…
SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms
Sirui Li, Shuai Wang, Zhijun Liu +3
Speech pre-processing techniques such as denoising, de-reverberation, and separation, are commonly employed as front-ends for various downstream speech processing tasks. However, t…