Tibetan-TTS:Low-Resource Tibetan Speech Synthesis with Large Model Adaptation

• URL: http://arxiv.org/abs/2605.02496v1
• Date: Mon, 04 May 2026 11:45:39 GMT
• Title: Tibetan-TTS:Low-Resource Tibetan Speech Synthesis with Large Model Adaptation
• Abstract summary: This work presents a large-model-based Tibetan TTS system built upon a large speech synthesis model developed by Xingchen AGI Lab.<n> Experimental results show that the system can generate stable, natural, and intelligible Tibetan speech under low-resource conditions.<n>Results demonstrate that combining a large-model backbone with Tibetan-oriented text representation adaptation and cross-lingual adaptive training enables highly usable low-resource Tibetan speech synthesis.
• Score: 12.646367121453485
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 pronunciation. To address these issues, this work presents, to the best of our knowledge, the first large-model-based Tibetan TTS system in the industry, built upon a large speech synthesis model developed by Xingchen AGI Lab. The proposed system integrates data quality enhancement, Tibetan-oriented text representation and tokenizer adaptation, and cross-lingual adaptive training for low-resource Tibetan speech synthesis. Experimental results show that the system can generate stable, natural, and intelligible Tibetan speech under low-resource conditions. In subjective evaluation, the MOS scores of the syllable-level and BPE-based systems reach 4.28 and 4.35, while their pronunciation accuracies reach 97.6% and 96.6%, respectively, outperforming an external commercial Tibetan TTS interface. These results demonstrate that combining a large-model backbone with Tibetan-oriented text representation adaptation and cross-lingual adaptive training enables highly usable low-resource Tibetan speech synthesis, and also provides a technical foundation for future unified multi-dialect Tibetan speech synthesis.

Related papers

• Align2Speak: Improving TTS for Low Resource Languages via ASR-Guided Online Preference Optimization [13.222167833914924]
  We propose a framework to adapt an autoregressive, multilingual TTS model to new languages.<n>We fine-tune this model on limited paired data of the new languages to capture the target language's prosodic features.<n>Experiments demonstrate that this pipeline produces intelligible and speaker-consistent speech in low-resource languages.
  arXiv  Detail & Related papers  (2025-09-26T00:28:50Z)
• TMD-TTS: A Unified Tibetan Multi-Dialect Text-to-Speech Synthesis for Ü-Tsang, Amdo and Kham Speech Dataset Generation [14.047778911628798]
  TMD-TTS is a unified Tibetan multi-dialect text-to-speech framework.<n>It synthesizes parallel dialectal speech from explicit dialect labels.
  arXiv  Detail & Related papers  (2025-09-22T17:38:52Z)
• BnTTS: Few-Shot Speaker Adaptation in Low-Resource Setting [9.335211682615213]
  This paper introduces BnTTS, the first framework for Bangla speaker adaptation-based TTS.<n>We pre-train BnTTS on 3.85k hours of Bangla speech dataset with corresponding text labels and evaluate performance in both zero-shot and few-shot settings.<n> Empirical evaluations in few-shot settings show that BnTTS significantly improves the naturalness, intelligibility, and speaker fidelity of synthesized Bangla speech.
  arXiv  Detail & Related papers  (2025-02-09T00:15:47Z)
• VoxHakka: A Dialectally Diverse Multi-speaker Text-to-Speech System for Taiwanese Hakka [10.784402571965867]
  VoxHakka is a text-to-speech (TTS) system designed for Taiwanese Hakka, a critically under-resourced language spoken in Taiwan. VoxHakka achieves high naturalness and accuracy and low real-time factor in speech synthesis.
  arXiv  Detail & Related papers  (2024-09-03T02:37:34Z)
• An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios [76.11409260727459]
  This paper explores the language adaptation capability of ZMM-TTS, a recent SSL-based multilingual TTS system. We demonstrate that the similarity in phonetics between the pre-training and target languages, as well as the language category, affects the target language's adaptation performance.
  arXiv  Detail & Related papers  (2024-06-13T08:16:52Z)
• ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation [79.66359274050885]
  We present ComSL, a speech-language model built atop a composite architecture of public pretrained speech-only and language-only models. Our approach has demonstrated effectiveness in end-to-end speech-to-text translation tasks.
  arXiv  Detail & Related papers  (2023-05-24T07:42:15Z)
• Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining [65.30528567491984]
  This paper proposes a method for zero-shot multilingual TTS using text-only data for the target language. The use of text-only data allows the development of TTS systems for low-resource languages. Evaluation results demonstrate highly intelligible zero-shot TTS with a character error rate of less than 12% for an unseen language.
  arXiv  Detail & Related papers  (2023-01-30T00:53:50Z)
• Any-speaker Adaptive Text-To-Speech Synthesis with Diffusion Models [65.28001444321465]
  Grad-StyleSpeech is an any-speaker adaptive TTS framework based on a diffusion model. It can generate highly natural speech with extremely high similarity to target speakers' voice, given a few seconds of reference speech. It significantly outperforms speaker-adaptive TTS baselines on English benchmarks.
  arXiv  Detail & Related papers  (2022-11-17T07:17:24Z)
• Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech [37.942466944970704]
  This paper proposes Virtuoso, a massively multilingual speech-text joint semi-supervised learning framework for text-to-speech synthesis (TTS) models. To train a TTS model from various types of speech and text data, different training schemes are designed to handle supervised (TTS and ASR data) and unsupervised (untranscribed speech and unspoken text) datasets. Experimental evaluation shows that multilingual TTS models trained on Virtuoso can achieve significantly better naturalness and intelligibility than baseline ones in seen languages.
  arXiv  Detail & Related papers  (2022-10-27T14:09:48Z)
• A Survey on Neural Speech Synthesis [110.39292386792555]
  Text to speech (TTS) is a hot research topic in speech, language, and machine learning communities. We conduct a comprehensive survey on neural TTS, aiming to provide a good understanding of current research and future trends. We focus on the key components in neural TTS, including text analysis, acoustic models and vocoders, and several advanced topics, including fast TTS, low-resource TTS, robust TTS, expressive TTS, and adaptive TTS, etc.
  arXiv  Detail & Related papers  (2021-06-29T16:50:51Z)
• LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition [148.43282526983637]
  We develop LRSpeech, a TTS and ASR system for languages with low data cost. We conduct experiments on an experimental language (English) and a truly low-resource language (Lithuanian) to verify the effectiveness of LRSpeech. We are currently deploying LRSpeech into a commercialized cloud speech service to support TTS on more rare languages.
  arXiv  Detail & Related papers  (2020-08-09T08:16:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.