Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody
Generating expressive and contextually appropriate prosody remains a challenge for modern text-to-speech (TTS) systems. This is particularly evident for long, multi-sentence inputs. In this paper, we examine simple extensions to a Transformer-based FastSpeech-like system, with the goal of improving prosody for multi-sentence TTS. We find that long context, powerful text features, and training on multi-speaker data all improve prosody. More interestingly, they result in synergies. Long context disambiguates prosody, improves coherence, and plays to the strengths of Transformers. Fine-tuning word-level features from a powerful language model, such as BERT, appears to profit from more training data, readily available in a multi-speaker setting. We look into objective metrics on pausing and pacing and perform thorough subjective evaluations for speech naturalness. Our main system, which incorporates all the extensions, achieves consistently strong results, including statistically significant improvements in speech naturalness over all its competitors.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingSentencetext-to-speechText to SpeechMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Text-aware and Context-aware Expressive Audiobook Speech Synthesis
Recent advances in text-to-speech have significantly improved the expressiveness of synthetic speech. However, a major challenge remains in generating speech that captures the diverse styles exhibited by professional nar…
Contrastive LearningLanguage ModelingLanguage ModellingSentence+3Bridging the Fairness Gap: Enhancing Pre-trained Models with LLM-Generated Sentences
Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversi…
AttributeDiversityFairnessIs Everything in Order? A Simple Way to Order Sentences
The task of organizing a shuffled set of sentences into a coherent text has been used to evaluate a machine's understanding of causal and temporal relations. We formulate the sentence ordering task as a conditional text-…
Conditional Text GenerationSentenceSentence OrderingText GenerationLinguistically Regularized LSTMs for Sentiment Classification
Sentiment understanding has been a long-term goal of AI in the past decades. This paper deals with sentence-level sentiment classification. Though a variety of neural network models have been proposed very recently, howe…
ClassificationGeneral ClassificationNegationSentence+2Generating Sentences from a Continuous Space
The standard recurrent neural network language model (RNNLM) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an RNN-based var…
Language ModelingLanguage ModellingSentence