Inference-time steering is crucial for deploying Large Language Models (LLMs) in real-world applications, where they must flexibly adjust behavior preferences. For instance, a model should dynamically adjust its caution level based on the risk of the scenario. This requirement introduces a challenge: modulating the int...
Ke-Qi Chen, Ze-Kai Sun, Yu-Hua Wen et al.· 0 citations
VoTSpeech is proposed, which decouples voice design from speech generation via an explicit intermediate voice latent, built on a shared language model backbone and performs strongly on InstructTTSEval-ZH, demonstrating competitive capabilities against strong open-source models while maintaining high naturalness.
Wen-Bing Yang, Qi-Hang Lu, Zi-Han Sun et al.· 0 citations
Speech emotion recognition (SER) is commonly formulated as direct utterance-to-label classification, leaving the acoustic and semantic evidence behind each prediction implicit. This letter proposes Attribute-Serialized Emotion Recognition (ASER), an attribute-serialized generative multi-task framework for SER, which or...
Ying-Ming Gao, Yi-Ming Gao, Rui-Xi Jiang et al.· IEEE Signal Processing Lette...· 0 citations
Low-resource text-to-speech (TTS) adaptation is constrained by scarce paired data and costly manual transcription. Existing fixed-voice TTS systems can provide relatively accurate pronunciation, but their synthetic speech offers limited speaker diversity and may exhibit flat prosody. Real recordings provide natural pro...
Jia-Yi Lu, Yi-Zhong Geng, Jing-Han Yang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
