← Back to all news
arXiv Machine Learning By Xilin Jiang, Shun Zhang, Tejas Jayashankar, Yinghao Aaron Li, Osama Hanna

Conversational Voice Aesthetic Model with Reinforcement Learning from Human Listeners

Read the original on arXiv Machine Learning →

The paper presents Conversational Voice Aesthetic Model (CVAM), a speech large language model that describes voice aesthetics in conversational contexts. CVAM predicts nine categorical attributes such as gender, pitch, pacing, emotion, and delivery, and is trained on human-annotated data from the CANDOR corpus. Experiments show that CVAM aligns better with human listeners than Gemini 3.1 Pro and other open‑source speech LLMs, demonstrating the value of grounding voice aesthetics in human perception.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Oct 1

Beyond Text: LLM-Based Dimensional Emotion Evaluation in Multimodal Dialogue

The paper introduces an LLM-based framework for continuous dimensional emotion evaluation in multimodal dialogue, combining discrete emotion recognition with Valence-Arousal-Dominance (VAD) assessment on the IEMOCAP dataset. It incorporates acoustic cues as natural language descriptions via the SpeechCueLLM approach and evaluates six models from the LLaMA, GPT, and Qwen families using zero-shot, few-shot, and LoRA fine-tuning. LoRA-fine-tuned LLaMA models outperform prompt-engineered GPT models, achieving a new state-of-the-art Valence CCC of 0.7822, and ablation studies show that textual audio descriptions significantly benefit smaller models. "whyItMatters":"The study demonstrates that domain adaptation through fine-tuning can surpass larger GPT models in multimodal emotion evaluation, highlighting the importance of tailored training for emotion recognition tasks."

By Yutong Hu, Jinho Choi
llmsfine-tuningmultimodalbenchmarks
More like this →
arXiv AI
Aug 11

Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions

arXiv:2608. 09930v1 Announce Type: cross Abstract: Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Models (Audio-LLM) judges) are expected to reflect human perception, yet it is unclear how well they capture the distinct aspects of speech that listeners actually perceive.

By Oluwanifemi Bamgbose, Simon Rosen, Jash Shah, Lindsay Devon Brin, Hoang H Nguyen, Anke Koelzer, Rachel Hansen, Tara Bogavelli, Fanny Riols
llmsmultimodalbenchmarks
More like this →