# Towards Spontaneous Style Modeling with Semi-supervised Pre-training for Conversational Text-to-Speech Synthesis

arXiv: https://arxiv.org/abs/2308.16593 · HTML: https://mlsanity.com/paper/2308.16593/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 31 Aug 2023.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset](https://mlsanity.com/paper/2203.16844/) (2022)
- [Conversational End-to-End TTS for Voice Agent](https://mlsanity.com/paper/2005.10438/) (2020)
- [Controllable Context-aware Conversational Speech Synthesis](https://mlsanity.com/paper/2106.10828/) (2021)
- [AdaSpeech 3: Adaptive Text to Speech for Spontaneous Style](https://mlsanity.com/paper/2107.02530/) (2021)
- [Prosody-controllable spontaneous TTS with neural HMMs](https://mlsanity.com/paper/2211.13533/) (2022)
- [The role of context in neural pitch accent detection in English](https://mlsanity.com/paper/2004.14846/) (2020)
- [End-to-End Text-to-Speech Based on Latent Representation of Speaking Styles Using Spontaneous Dialogue](https://mlsanity.com/paper/2206.12040/) (2022)
- [ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in Paragraph-based TTS](https://mlsanity.com/paper/2209.06484/) (2022)
- [Transplantation of Conversational Speaking Style with Interjections in Sequence-to-Sequence Speech Synthesis](https://mlsanity.com/paper/2207.12262/) (2022)
- [Semi-Supervised Learning Based on Reference Model for Low-resource TTS](https://mlsanity.com/paper/2210.14723/) (2022)

## Built on by (most cited first, 4 of 4)

- [CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations](https://mlsanity.com/paper/2404.06690/) (2024)
- [Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models](https://mlsanity.com/paper/2407.13509/) (2024)
- [Integrating Feedback Loss from Bi-modal Sarcasm Detector for Sarcastic Speech Synthesis](https://mlsanity.com/paper/2508.13028/) (2025)
- [Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language Model](https://mlsanity.com/paper/2309.11000/) (2023)

## Abstract (arXiv)

The spontaneous behavior that often occurs in conversations makes speech more human-like compared to reading-style. However, synthesizing spontaneous-style speech is challenging due to the lack of high-quality spontaneous datasets and the high cost of labeling spontaneous behavior. In this paper, we propose a semi-supervised pre-training method to increase the amount of spontaneous-style speech and spontaneous behavioral labels. In the process of semi-supervised learning, both text and speech information are considered for detecting spontaneous behaviors labels in speech. Moreover, a linguistic-aware encoder is used to model the relationship between each sentence in the conversation. Experimental results indicate that our proposed method achieves superior expressive speech synthesis performance with the ability to model spontaneous behavior in spontaneous-style speech and predict reasonable spontaneous behavior from text.