Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models

With the advent of the big data and large language model era, zero-shot personalized rapid customization has emerged as a significant trend. In this report, we introduce Takin AudioLLM, a series of techniques and models, mainly including Takin TTS, Takin VC, and Takin Morphing, specifically designed...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-09
Hauptverfasser:	Chen, Sijing, Yuan, Feng, He, Laipeng, He, Tianwei, He, Wendi, Hu, Yanni, Lin, Bin, Lin, Yiting, Pan, Yu, Tan, Pengfei, Tian, Chengwei, Wang, Chen, Wang, Zhicheng, Xie, Ruoye, Yao, Jixun, Quanlei Yan, Yang, Yuguang, Ye, Jianhao, Yin, Jingjing, Yu, Yanzhen, Zhang, Huimin, Zhang, Xiang, Zhao, Guangcheng, Zhou, Hongbin, Zou, Pengpeng
Format:	Artikel
Sprache:	eng
Schlagworte:	Codec Controllability Effectiveness Large language models Linguistics Modelling Morphing Robust control Speech Speech recognition
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!