An investigation of phrase break prediction in an End-to-End TTS system
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915128447860736 |
|---|---|
| author | Vadapalli, Anandaswarup |
| author_facet | Vadapalli, Anandaswarup |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_04157 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | An investigation of phrase break prediction in an End-to-End TTS system Vadapalli, Anandaswarup Audio and Speech Processing Computation and Language Sound 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. |
| title | An investigation of phrase break prediction in an End-to-End TTS system |
| topic | Audio and Speech Processing Computation and Language Sound |
| url | https://arxiv.org/abs/2304.04157 |