paper-with-me

홈 › Papers

Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody

2022-06-29 · Peter Makarov, Ammar Abbas, Mateusz Łajszczak, Arnaud Joly, Sri Karlapati, Alexis Moinet, Thomas Drugman, Penny Karanasou

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.

📄 PDF Abstract BibTeX arXiv:2206.14643

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingSentencetext-to-speechText to Speech

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
WordPiece 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Text-aware and Context-aware Expressive Audiobook Speech Synthesis

2024-06-09 · Dake Guo, Xinfa Zhu, Liumeng Xue, Yongmao Zhang 외

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+3

Bridging the Fairness Gap: Enhancing Pre-trained Models with LLM-Generated Sentences

2025-01-12 · Liu Yu, Ludie Guo, Ping Kuang, Fan Zhou

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…

AttributeDiversityFairness

Is Everything in Order? A Simple Way to Order Sentences

2021-04-14 · EMNLP 2021 11 · Somnath Basu Roy Chowdhury, Faeze Brahman, Snigdha Chaturvedi

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 Generation

Linguistically Regularized LSTMs for Sentiment Classification

2016-11-12 · Qiao Qian, Minlie Huang, Jinhao Lei, Xiaoyan Zhu

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+2

Generating Sentences from a Continuous Space

2015-11-19 · CONLL 2016 8 · Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, Andrew M. Dai 외

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