EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech
State-of-the-art speech synthesis models try to get as close as possible to the human voice. Hence, modelling emotions is an essential part of Text-To-Speech (TTS) research. In our work, we selected FastSpeech2 as the starting point and proposed a series of modifications for synthesizing emotional speech. According to automatic and human evaluation, our model, EmoSpeech, surpasses existing models regarding both MOS score and emotion recognition accuracy in generated speech. We provided a detailed ablation study for every extension to FastSpeech2 architecture that forms EmoSpeech. The uneven distribution of emotions in the text is crucial for better, synthesized speech and intonation perception. Our model includes a conditioning mechanism that effectively handles this issue by allowing emotions to contribute to each phone with varying intensity levels. The human assessment indicates that proposed modifications generate audio with higher MOS and emotional expressiveness.
Code (1)
Tasks
Emotion RecognitionSpeech Synthesistext-to-speechText to SpeechSimilar Papers 제목 키워드 기반
EmoSpeech: A Corpus of Emotionally Rich and Contextually Detailed Speech Annotations
Advances in text-to-speech (TTS) technology have significantly improved the quality of generated speech, closely matching the timbre and intonation of the target speaker. However, due to the inherent complexity of human …
text-to-speechText to SpeechCausal Prosody Mediation for Text-to-Speech:Counterfactual Training of Duration, Pitch, and Energy in FastSpeech2
We propose a novel causal prosody mediation framework for expressive text-to-speech (TTS) synthesis. Our approach augments the FastSpeech2 architecture with explicit emotion conditioning and introduces counterfactual tra…
Speech SynthesisFastSpeech 2: Fast and High-Quality End-to-End Text to Speech
Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an auto…
Knowledge DistillationSpeech Synthesistext-to-speechText to Speech+1An Empirical Study on Learning Latent Representations for Emotional Speech Synthesis
For the last couple of years, the field of speech synthesis has improved dramatically thanks to deep learning. There are more and more deep learning-based TTS systems developed to make it possible to produce voices with …
Speech SynthesisEmotional Prosody Control for Speech Generation
Machine-generated speech is characterized by its limited or unnatural emotional variation. Current text to speech systems generates speech with either a flat emotion, emotion selected from a predefined set, average varia…
text-to-speechText to Speech