An investigation of phrase break prediction in an End-to-End TTS system
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.
Code (2)
Tasks
Predictiontext-to-speechText to SpeechSimilar Papers 제목 키워드 기반
Cross-Lingual Transfer Learning for Phrase Break Prediction with Multilingual Language Model
Phrase break prediction is a crucial task for improving the prosody naturalness of a text-to-speech (TTS) system. However, most proposed phrase break prediction models are monolingual, trained exclusively on a large amou…
Cross-Lingual TransferLanguage ModelingLanguage ModellingPrediction+3Synthetic Data Generation for Phrase Break Prediction with Large Language Model
Current approaches to phrase break prediction address crucial prosodic aspects of text-to-speech systems but heavily rely on vast human annotations from audio or text, incurring significant manual effort and cost. Inhere…
Synthetic Data GenerationPhrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis
We propose a novel phrase break prediction method that combines implicit features extracted from a pre-trained large language model, a.k.a BERT, and explicit features extracted from BiLSTM with linguistic features. In co…
Language ModelingLanguage ModellingLarge Language ModelSentence+4Open-Source Boundary-Annotated Corpus for Arabic Speech and Language Processing
A boundary-annotated and part-of-speech tagged corpus is a prerequisite for developing phrase break classifiers. Boundary annotations in English speech corpora are descriptive, delimiting intonation units perceived by th…
ChunkingDescriptiveSpeech SynthesisText-To-Speech SynthesisA LSTM Approach with Sub-Word Embeddings for Mongolian Phrase Break Prediction
In this paper, we first utilize the word embedding that focuses on sub-word units to the Mongolian Phrase Break (PB) prediction task by using Long-Short-Term-Memory (LSTM) model. Mongolian is an agglutinative language. E…
Dictionary LearningMachine TranslationQuestion AnsweringWord Embeddings