mlsanityData to 7 Oct 2026

Multilingual context-based pronunciation learning for Text-to-Speech

arXiv 2307.16709 ↗First posted 31 Jul 2023cs.CL eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

Phonetic information and linguistic knowledge are an essential component of a Text-to-speech (TTS) front-end. Given a language, a lexicon can be collected offline and Grapheme-to-Phoneme (G2P) relationships are usually modeled in order to predict the pronunciation for out-of-vocabulary (OOV) words. Additionally, post-lexical phonology, often defined in the form of rule-based systems, is used to correct pronunciation within or between words. In this work we showcase a multilingual unified front-end system that addresses any pronunciation related task, typically handled by separate modules. We evaluate the proposed model on G2P conversion and other language-specific challenges, such as homograph and polyphones disambiguation, post-lexical rules and implicit diacritization. We find that the multilingual model is competitive across languages and tasks, however, some trade-offs exists when compared to equivalent monolingual solutions.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 15 of its 34 references that are in the map. First posted on arXiv 31 Jul 2023.

Builds on

15 of 34 references.

References · 15

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2022ByT5 model for massively multilingual grapheme-to-phoneme conversioncited by 49
  4. 2020Applying the Transformer to Character-level Transductioncited by 43
  5. 2020Transformer based Grapheme-to-Phoneme Conversioncited by 32
  6. 2019Arabic Text Diacritization Using Deep Neural Networkscited by 18
  7. 2020Unified Mandarin TTS Front-end Based on Distilled BERT Modelcited by 18
  8. 2017Massively Multilingual Neural Grapheme-to-Phoneme Conversioncited by 15
  9. 2022SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguationcited by 14
  10. 2019A unified sequence-to-sequence front-end model for Mandarin text-to-speech synthesiscited by 8
  11. 2020Scalable Multilingual Frontend for TTScited by 8
  12. 2022g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarincited by 7
3 more
  1. 2021Improving Arabic Diacritization by Learning to Diacritize and Translatecited by 6
  2. 2022Neural Grapheme-to-Phoneme Conversion with Pre-trained Grapheme Modelscited by 4
  3. 2022A Polyphone BERT for Polyphone Disambiguation in Mandarin Chinesecited by 1

Built on by

Cited by year

Citing papers per year: 2024: 2.

2 papers.

  1. 2024Acquiring Pronunciation Knowledge from Transcribed Speech Audio via Multi-task Learningcited by 1
  2. 2024A Two-Step Approach for Data-Efficient French Pronunciation Learningcited by 0