Searcharxiv⌕ Search

arXiv subjects

Wangzixi Zhou

Publications and source records attributed to Wangzixi Zhou.

4 recordsLinked to original sources

DialInstruct-TTS: Interactive Expressive Speech Generation via Multi-Turn Dialogue with Fine-Grained Temporal Control

Existing instruction-based TTS systems primarily support one-shot, utterance-level control, where a single instruction determines the speaking style of an entire utterance. As a result, even minor refinements require rewriting the instruction and regenerating the full utterance, limiting fine-grained interactive control. We propose DialInstruct-TTS, an interactive multi-turn expressive TTS framework that enables users to iteratively refine generated speech through natural-language dialogue until the desired style is achieved. At each dialogue turn, a Qwen-based planner integrates the dialogue history and latest user instruction into a complete TemporalPlan, while a temporal acoustic control module provides fine-grained control over emotion, speaking rate, volume, and phonation. Reference-latent revision preserves non-target regions across turns, allowing users to modify only the requested attributes or temporal spans while retaining previously satisfactory speech. Subjective evaluations demonstrate improved global instruction following, accurate local style realization, and effective non-target preservation. Compared with conventional one-shot interaction requiring full instruction restatement and utterance regeneration, DialInstruct-TTS substantially improves perceived convenience and interaction comfort. Audio samples are available at https://anonymous.4open.science/w/eacl-demo-17C5/.

eess.AS↗

Beyond One-Size-Fits-All: Personalized and Culturally Adaptive Emotional TTS via Interactive Optimization of Individual Emotion Perception Spaces

The rise of conversational AI has increased interest in emotional Text-to-Speech (TTS). Most systems rely on discrete emotion labels, which fail to capture the nuanced nature of human affect. Recent models employ dimensional representations such as Russell's arousal-valence (A-V) model, offering finer control. However, emotional perception varies across individuals and cultures, which may cause mismatches between modeled and perceived emotions. We propose a personalized and culturally adaptive emotional TTS framework that performs interactive optimization of individualized A-V perception spaces using an Interactive Genetic Algorithm. By adapting emotion representations to each listener, the system produces speech with more perceptually aligned emotional expression than models using averaged A-V values. Evaluations with Japanese, Chinese, and Indonesian participants highlight the importance of personalization and cultural adaptation for moving beyond one-size-fits-all emotional TTS.

eess.AS↗

WaveNeXt 2: ConvNeXt-Based Fast Neural Vocoders With Residual Denoising and Sub-Modeling for GAN and Diffusion Models

Most neural vocoders are limited to one type: either GAN or diffusion-based. While state-of-the-art models like Vocos and WaveNeXt use powerful ConvNeXt-based generators, they have only been used in GAN frameworks and have limited performance in multi-speaker settings. Moreover, diffusion models, despite training faster than GANs, have slow CPU inference. In this paper, we introduce WaveNeXt 2, a unified ConvNeXt-based framework compatible with both GAN and diffusion vocoders. Its core innovation is residual denoising and sub-modeling, where each sub-model progressively refines the waveform. Experimental results in the multi-speaker dataset demonstrate the effectiveness of our approach: (1) GAN-WaveNeXt 2 is much faster than HiFi-GAN and WaveFit, and (2) Diff-WaveNeXt 2 also delivers much faster inference and competitive synthesis quality compared with FastDiff with 4 steps. The Diff-WaveNeXt 2 is very training-efficient, training in only 32 hours, making it ideal for resource-constrained applications.

eess.AS↗

Toward Natural Emotional Text-To-Speech System with Fine-Grained Non-Verbal Expression Control

While current emotional Text-to-Speech (TTS) models have successfully controlled verbal prosody, they often ignore non-verbal vocalizations (NVs), which are essential for authentic human emotion. Although some non-verbal datasets have recently emerged, they often lack high-quality, fine-grained annotations, which restricts a model's ability to precisely control NV generation. To address this limitation, we propose a novel approach for fine-grained non-verbal expression synthesis. We curate and reprocess female NV utterances from the EARS corpus, develop a new annotation scheme using tags to encode NV types, frequencies, and durations, and build an emotional TTS benchmark to demonstrate its effectiveness. Our evaluation shows that while our NV approach leads to minor trade-offs in perceived naturalness, it significantly improves expressiveness (eMOS 4.20) and emotional recognition accuracy (78.8%). Emotion-specific analysis further reveals that NV cues are highly effective for high-arousal emotions like happy (82.5%) and fear (82.7%), and almost perfectly convey sadness (98.3%).

eess.AS↗