This paper introduces Spark-Audio 1.0, a speech foundation model trained on domestically produced computing infrastructure. The model accepts text and speech inputs and generates text outputs. It supports multilingual (99 languages) and multi-dialect (202 dialects) speech recognition, speech translation, audio percepti...
Chen-Yue Zhang, Cong Liu, Ding-Shu Tian et al.· 0 citations
Lipreading remains challenging due to the inherent ambiguity of visual speech cues and their sensitivity to head pose and video resolution. In this work, we propose FLARE, a framework for robust visual speech representation learning via cross-modal distillation and joint face-lip modeling. FLARE leverages semantically...
Jing-Xuan Zhang, Gen-Shun Wan, Jian-Qing Gao et al.· 0 citations
LLM-HB is proposed, a language-aware large language model-guided hotword biasing framework for code-switching ASR (CS-ASR), which incorporates a mixture-of-experts (MoE) adaptor and an auxiliary language prediction head to better capture and differentiate multilingual representations.
Yuxuan He, Gen-Shun Wan, Peng-Cheng Li et al.· 0 citations
Post-training quantization reduces the deployment cost of vision-language models (VLMs), but preserving multimodal capabilities at low bit widths remains challenging. Existing methods rely on modality- or token-level gradient statistics, which are susceptible to cross-sample variations in visual-to-textual token ratios...