Investigating Neural Audio Codecs for Speech Language Model-Based Speech Generation

Autor:	Li, Jiaqi, Wang, Dongmei, Wang, Xiaofei, Qian, Yao, Zhou, Long, Liu, Shujie, Yousefi, Midia, Li, Canrun, Tsai, Chung-Hsien, Xiao, Zhen, Liu, Yanqing, Chen, Junkun, Zhao, Sheng, Li, Jinyu, Wu, Zhizheng, Zeng, Michael
Rok vydání:	2024
Předmět:	Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	Neural audio codec tokens serve as the fundamental building blocks for speech language model (SLM)-based speech generation. However, there is no systematic understanding on how the codec system affects the speech generation performance of the SLM. In this work, we examine codec tokens within SLM framework for speech generation to provide insights for effective codec design. We retrain existing high-performing neural codec models on the same data set and loss functions to compare their performance in a uniform setting. We integrate codec tokens into two SLM systems: masked-based parallel speech generation system and an auto-regressive (AR) plus non-auto-regressive (NAR) model-based system. Our findings indicate that better speech reconstruction in codec systems does not guarantee improved speech generation in SLM. A high-quality codec decoder is crucial for natural speech production in SLM, while speech intelligibility depends more on quantization mechanism. Comment: Accepted by SLT-2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2409.04016 Zobrazit plný text záznamu View this record from Arxiv