4 papers
Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM
Fengrun Zhang, Wang Geng, Hukai Huang +3
In this paper, we introduce a speech-conditioned Large Language Model (LLM) integrated with a Mixture of Experts (MoE) based connector to address the challenge of Code-Switching (C…
Zero-Shot Sing Voice Conversion: built upon clustering-based phoneme representations
Wangjin Zhou, Fengrun Zhang, Yiming Liu +3
This study presents an innovative Zero-Shot any-to-any Singing Voice Conversion (SVC) method, leveraging a novel clustering-based phoneme representation to effectively separate con…
Dynamic Language Group-Based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing
Hukai Huang, Shenghui Lu, Yahui Shan +5
The Mixture of Experts (MoE) model is a promising approach for handling code-switching speech recognition (CS-ASR) tasks. However, the existing CS-ASR work on MoE has yet to levera…
Minimally-Supervised Speech Synthesis with Conditional Diffusion Model and Language Model: A Comparative Study of Semantic Coding
Chunyu Qiang, Hao Li, Hao Ni +5
Recently, there has been a growing interest in text-to-speech (TTS) methods that can be trained with minimal supervision by combining two types of discrete speech representations a…