An investigation of phrase break prediction in an End-to-End TTS system
Not on the map. Why?
Abstract (arXiv)
Purpose: This work explores the use of external phrase break prediction models to enhance listener comprehension in End-to-End Text-to-Speech (TTS) systems. Methods: The effectiveness of these models is evaluated based on listener preferences in subjective tests. Two approaches are explored: (1) a bidirectional LSTM model with task-specific embeddings trained from scratch, and (2) a pre-trained BERT model fine-tuned on phrase break prediction. Both models are trained on a multi-speaker English corpus to predict phrase break locations in text. The End-to-End TTS system used comprises a Tacotron2 model with Dynamic Convolutional Attention for mel spectrogram prediction and a WaveRNN vocoder for waveform generation. Results: The listening tests show a clear preference for text synthesized with predicted phrase breaks over text synthesized without them. Conclusion: These results confirm the value of incorporating external phrasing models within End-to-End TTS to enhance listener comprehension.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 14 of its 48 references that are in the map. First posted on arXiv 9 Apr 2023.
Builds on
14 of 48 references.
References · 14
- 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 737
- 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 639
- 2018Efficient Neural Audio Synthesiscited by 218
- 2023Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervisioncited by 167
- 2018Hierarchical Generative Modeling for Controllable Speech Synthesiscited by 93
- 2018Learning latent representations for style control and transfer in end-to-end speech synthesiscited by 61
- 2018Robust and fine-grained prosody control of end-to-end speech synthesiscited by 48
- 2019Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesiscited by 44
- 2019Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokenscited by 44
- 2019Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesiscited by 15
- 2021Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesiscited by 12
- 2020Unsupervised Style and Content Separation by Minimizing Mutual Information for Speech Synthesiscited by 11
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.