Scholarlink

<p>This work explores the use of external phrase break prediction models to enhance listener comprehension in end-to-end text-to-speech (TTS) systems. 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. The listening tests show a clear preference for text synthesized with predicted phrase breaks over text synthesized without them. These results confirm the value of incorporating external phrasing models within end-to-end TTS to enhance listener comprehension.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Investigation of Phrase Break Prediction in an End-to-End TTS System

  • 期刊论文

  • 发表日期：

    2025年1月22日

查看全文
  • Anandaswarup Vadapalli

摘要

This work explores the use of external phrase break prediction models to enhance listener comprehension in end-to-end text-to-speech (TTS) systems. 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. The listening tests show a clear preference for text synthesized with predicted phrase breaks over text synthesized without them. These results confirm the value of incorporating external phrasing models within end-to-end TTS to enhance listener comprehension.