Exploring Speech Style Spaces With Language Models: Emotional TTS Without Emotion Labels

Abstract

Many frameworks for emotional text-to-speech (E-TTS) rely on human-annotated emotion labels that are often inaccurate and difficult to obtain. Learning emotional prosody implicitly presents a tough challenge due to the subjective nature of emotions. In this study, we propose a novel approach that leverages text awareness to acquire emotional styles without the need for explicit emotion labels or text prompts. We present TEMOTTS, a two-stage framework for E-TTS that is trained without emotion labels and is capable of inference without auxiliary inputs. Our proposed method performs knowledge transfer between the linguistic space learned by BERT and the emotional style space constructed by global style tokens. Our experimental results demonstrate the effectiveness of our proposed framework, showcasing improvements in emotional accuracy and naturalness. This is one of the first studies to leverage the emotional correlation between spoken content and expressive delivery for emotional TTS.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychandra2024exploring

Related papers

• Emosphere-tts: Emotional Style And Intensity Modeling Via Spherical Emotion Vector For Controllable Emotional Text-to-speech (2024)10.35
• Emotional Dimension Control In Language Model-based Text-to-speech: Spanning A Broad Spectrum Of Human Emotions (2024)0.00
• Text-driven Emotional Style Control And Cross-speaker Style Transfer In Neural TTS (2022)7.81
• Self-supervised Context-aware Style Representation For Expressive Speech Synthesis (2022)6.34
• Instructtts: Modelling Expressive TTS In Discrete Latent Space With Natural Language Style Prompt (2023)0.00
• Msemotts: Multi-scale Emotion Transfer, Prediction, And Control For Emotional Speech Synthesis (2022)13.97
• Language Model-based Emotion Prediction Methods For Emotional Speech Synthesis Systems (2022)8.35
• Expressive Text-to-speech Using Style Tag (2021)10.85