4 papers · 1 filter
Emo-BPO: Emotion Bidirectional Preference Optimization for Diffusion-based Emotional TTS
Jiacheng Shi, Hongfei Du, Xinyuan Song +3
Diffusion-based TTS has demonstrated strong capability in emotional speech generation. However, existing emotion alignment methods primarily reinforce target emotional expressions…
Tracing a Sparse Emotion-Control Circuit in LLM-Based Text-to-Speech
Hongfei Du, Jiacheng Shi, Yanfu Zhang +1
LLM-based text-to-speech (TTS) models can generate emotionally expressive speech, but how reference emotion is routed through the model and realized in decoded speech remains uncle…
AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling
Jiacheng Shi, Hongfei Du, Xinyuan Song +3
Neural speech codecs provide discrete representations for speech language models, but emotional cues are often degraded during quantization. Existing codecs mainly optimize acousti…
EMO-TTA: Improving Test-Time Adaptation of Audio-Language Models for Speech Emotion Recognition
Jiacheng Shi, Hongfei Du, Y. Alicia Hong +1
Speech emotion recognition (SER) with audio-language models (ALMs) remains vulnerable to distribution shifts at test time, leading to performance degradation in out-of-domain scena…