mlsanityData to 7 Oct 2026

End-to-end Text-to-speech for Low-resource Languages by Cross-Lingual Transfer Learning

arXiv 1904.06508 ↗First posted 13 Apr 2019cs.CL cs.LG cs.SDcited by 30

Not on the map. Why?

Abstract (arXiv)

End-to-end text-to-speech (TTS) has shown great success on large quantities of paired text plus speech data. However, laborious data collection remains difficult for at least 95% of the languages over the world, which hinders the development of TTS in different languages. In this paper, we aim to build TTS systems for such low-resource (target) languages where only very limited paired data are available. We show such TTS can be effectively constructed by transferring knowledge from a high-resource (source) language. Since the model trained on source language cannot be directly applied to target language due to input space mismatch, we propose a method to learn a mapping between source and target linguistic symbols. Benefiting from this learned mapping, pronunciation information can be preserved throughout the transferring procedure. Preliminary experiments show that we only need around 15 minutes of paired data to obtain a relatively good TTS system. Furthermore, analytic studies demonstrated that the automatically discovered mapping correlate well with the phonetic expertise.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 11; 2023: 4; 2024: 6; 2025: 2; 2026: 1.

30 papers.

Sort:

By area:

  1. 2021A Survey on Neural Speech Synthesiscited by 182
  2. 2022Towards Building Text-To-Speech Systems for the Next Billion Userscited by 27
  3. 2022Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Featurescited by 20
  4. 2022Low-Resource Multilingual and Zero-Shot Multispeaker TTScited by 15
  5. 2021Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speechcited by 14
  6. 2021Multilingual Byte2Speech Models for Scalable Low-resource Speech Synthesiscited by 13
  7. 2021KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Datasetcited by 13
  8. 2022KazakhTTS2: Extending the Open-Source Kazakh TTS Corpus With More Data, Speakers, and Topicscited by 10
  9. 2024Meta Learning Text-to-Speech Synthesis in over 7000 Languagescited by 9
  10. 2022Voice Filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing modulecited by 8
  11. 2022Improved Meta Learning for Low Resource Speech Recognitioncited by 7
  12. 2021Review of end-to-end speech synthesis technology based on deep learningcited by 6
18 more
  1. 2022Distribution augmentation for low-resource expressive text-to-speechcited by 5
  2. 2022Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS)cited by 5
  3. 2023Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case Studycited by 4
  4. 2024Improving Low-Resource Knowledge Tracing Tasks by Supervised Pre-training and Importance Mechanism Fine-tuningcited by 3
  5. 2024A multilingual training strategy for low resource Text to Speechcited by 3
  6. 2025Zero-Shot Text-to-Speech for Vietnamesecited by 3
  7. 2021Towards Lifelong Learning of Multilingual Text-To-Speech Synthesiscited by 2
  8. 2022MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baselinecited by 2
  9. 2023Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliterationcited by 2
  10. 2023Strategies in Transfer Learning for Low-Resource Speech Synthesis: Phone Mapping, Features Input, and Source Language Selectioncited by 2
  11. 2022Few-Shot Cross-Lingual TTS Using Transferable Phoneme Embeddingcited by 1
  12. 2022Towards High-Quality Neural TTS for Low-Resource Languages by Learning Compact Speech Representationscited by 1
  13. 2024Text2Data: Low-Resource Data Generation with Textual Controlcited by 1
  14. 2025Align2Speak: Improving TTS for Low Resource Languages via ASR-Guided Online Preference Optimizationcited by 1
  15. 2023The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speechcited by 0
  16. 2024Maximizing Data Efficiency for Cross-Lingual TTS Adaptation by Self-Supervised Representation Mixing and Embedding Initializationcited by 0
  17. 2024LIMBA: An Open-Source Framework for the Preservation and Valorization of Low-Resource Languages using Generative Modelscited by 0
  18. 2026LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgishcited by 0