Enhancing Emotional Text-to-speech Controllability With Natural Language Guidance Through Contrastive Learning And Diffusion Models

Abstract

While current emotional text-to-speech (TTS) systems can generate highly intelligible emotional speech, achieving fine control over emotion rendering of the output speech still remains a significant challenge. In this paper, we introduce ParaEVITS, a novel emotional TTS framework that leverages the compositionality of natural language to enhance control over emotional rendering. By incorporating a text-audio encoder inspired by ParaCLAP, a contrastive language-audio pretraining (CLAP) model for computational paralinguistics, the diffusion model is trained to generate emotional embeddings based on textual emotional style descriptions. Our framework first trains on reference audio using the audio encoder, then fine-tunes a diffusion model to process textual inputs from ParaCLAP's text encoder. During inference, speech attributes such as pitch, jitter, and loudness are manipulated using only textual conditioning. Our experiments demonstrate that ParaEVITS effectively control emotion rende

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keyjing2024enhancing

Related papers

• Fine-grained Emotional Control Of Text-to-speech: Learning To Rank Inter- And Intra-class Emotion Intensities (2023)6.77
• Emodiff: Intensity Controllable Emotional Text-to-speech With Soft-label Guidance (2022)0.00
• VECL-TTS: Voice Identity And Emotional Style Controllable Cross-lingual Text-to-speech (2024)0.00
• Emomix: Emotion Mixing Via Diffusion Models For Emotional Speech Synthesis (2023)0.00
• Emotion-aligned Generation In Diffusion Text To Speech Models Via Preference-guided Optimization (2025)2.26
• Emotional Dimension Control In Language Model-based Text-to-speech: Spanning A Broad Spectrum Of Human Emotions (2024)0.00
• PAVITS: Exploring Prosody-aware VITS For End-to-end Emotional Voice Conversion (2024)8.35
• PROEMO: Prompt-driven Text-to-speech Synthesis Based On Emotion And Intensity Control (2025)0.00