5 papers
Tibetan-TTS:Low-Resource Tibetan Speech Synthesis with Large Model Adaptation
Jiaxu He, Chao Wang, Jie Lian +4
Tibetan text-to-speech (TTS) has long been challenged by scarce speech resources, significant dialectal variation, and the complex mapping between written text and spoken pronuncia…
Context-Aware Dynamic Chunking for Streaming Tibetan Speech Recognition
Chao Wang, Yuqing Cai, Renzeng Duojie +3
In this work, we propose a streaming speech recognition framework for Amdo Tibetan, built upon a hybrid CTC/Atten-tion architecture with a context-aware dynamic chunking mechanism.…
Listening, Imagining & Refining: A Heuristic Optimized ASR Correction Framework with LLMs
Yutong Liu, Ziyue Zhang, Cheng Huang +4
Automatic Speech Recognition (ASR) systems remain prone to errors that affect downstream applications. In this paper, we propose LIR-ASR, a heuristic optimized iterative correction…
TMD-TTS: A Unified Tibetan Multi-Dialect Text-to-Speech Framework for Ü-Tsang, Amdo and Kham Speech Dataset Generation
Yutong Liu, Ziyue Zhang, Ban Ma-bao +7
Tibetan is a low-resource language with limited parallel speech corpora spanning its three major dialects (Ü-Tsang, Amdo, and Kham), limiting progress in speech modeling. To addres…
FMSD-TTS: Few-shot Multi-Speaker Multi-Dialect Text-to-Speech Synthesis for Ü-Tsang, Amdo and Kham Speech Dataset Generation
Yutong Liu, Ziyue Zhang, Ban Ma-bao +7
Tibetan is a low-resource language with minimal parallel speech corpora spanning its three major dialects-Ü-Tsang, Amdo, and Kham-limiting progress in speech modeling. To address t…