Loading Now

Summary of Towards Controllable Speech Synthesis in the Era Of Large Language Models: a Survey, by Tianxin Xie et al.


Towards Controllable Speech Synthesis in the Era of Large Language Models: A Survey

by Tianxin Xie, Yan Rong, Pengfei Zhang, Li Liu

First submitted to arxiv on: 9 Dec 2024

Categories

  • Main: Computation and Language (cs.CL)
  • Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multimedia (cs.MM); Sound (cs.SD); Audio and Speech Processing (eess.AS)

     Abstract of paper      PDF of paper


GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty Written by Summary
High Paper authors High Difficulty Summary
Read the original abstract here
Medium GrooveSquid.com (original content) Medium Difficulty Summary
This paper presents a comprehensive survey of controllable text-to-speech (TTS) technologies, which have evolved beyond generating human-like speech to enable fine-grained control over various attributes such as emotion, prosody, timbre, and duration. The authors examine the general pipeline, challenges, model architectures, and control strategies used in controllable TTS, providing a taxonomy of existing methods. They also summarize datasets and evaluation metrics, highlighting applications and future directions.
Low GrooveSquid.com (original content) Low Difficulty Summary
Controllable text-to-speech (TTS) lets computers create speech that sounds natural and can even be controlled to have certain emotions or tones. Researchers are working on making this technology better by giving it more control over the way the speech sounds. This paper looks at all the different ways people are trying to make controllable TTS work, from basic techniques to using big language models. It also talks about the challenges and problems that need to be solved to make it happen.

Keywords

» Artificial intelligence