mlsanityData to 7 Oct 2026

Phonological Features for 0-shot Multilingual Speech Synthesis

arXiv 2008.04107 ↗First posted 6 Aug 2020eess.AS cs.LG cs.SDcited by 20

Not on the map. Why?

Abstract (arXiv)

Code-switching---the intra-utterance use of multiple languages---is prevalent across the world. Within text-to-speech (TTS), multilingual models have been found to enable code-switching. By modifying the linguistic input to sequence-to-sequence TTS, we show that code-switching is possible for languages unseen during training, even within monolingual models. We use a small set of phonological features derived from the International Phonetic Alphabet (IPA), such as vowel height and frontness, consonant place and manner. This allows the model topology to stay unchanged for different languages, and enables new, previously unseen feature combinations to be interpreted by the model. We show that this allows us to generate intelligible, code-switched speech in a new language at test time, including the approximation of sounds never seen in training.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 5; 2023: 5; 2024: 3; 2025: 1; 2026: 1.

20 papers.

Sort:

  1. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
  2. 2021A Survey on Neural Speech Synthesiscited by 182
  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. 2021Multilingual Byte2Speech Models for Scalable Low-resource Speech Synthesiscited by 13
  6. 2026[b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmeticcited by 11
  7. 2023Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretrainingcited by 10
  8. 2021Cross-lingual Low Resource Speaker Adaptation Using Phonological Featurescited by 8
  9. 2022Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS)cited by 5
  10. 2021Revisiting IPA-based Cross-lingual Text-to-speechcited by 4
  11. 2024Generating Feature Vectors from Phonetic Transcriptions in Cross-Linguistic Data Formatscited by 4
  12. 2023CrossSpeech: Speaker-independent Acoustic Representation for Cross-lingual Speech Synthesiscited by 3
8 more
  1. 2023Strategies in Transfer Learning for Low-Resource Speech Synthesis: Phone Mapping, Features Input, and Source Language Selectioncited by 2
  2. 2025MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discoverycited by 1
  3. 2021Applying Phonological Features in Multilingual Text-To-Speechcited by 0
  4. 2022Data-augmented cross-lingual synthesis in a teacher-student frameworkcited by 0
  5. 2022Integrating Human Linguistic Insights into AI: Theory-Driven Representation for Multilingual Text-to-Speechcited by 0
  6. 2023The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speechcited by 0
  7. 2024PRESENT: Zero-Shot Text-to-Prosody Controlcited by 0
  8. 2024CrossSpeech++: Cross-lingual Speech Synthesis with Decoupled Language and Speaker Generationcited by 0