mlsanityData to 7 Oct 2026

Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features

arXiv 2203.03191 ↗First posted 7 Mar 2022cs.CL cs.LG eess.AScited by 20

Not on the map. Why?

Abstract (arXiv)

While neural text-to-speech systems perform remarkably well in high-resource scenarios, they cannot be applied to the majority of the over 6,000 spoken languages in the world due to a lack of appropriate training data. In this work, we use embeddings derived from articulatory vectors rather than embeddings derived from phoneme identities to learn phoneme representations that hold across languages. In conjunction with language agnostic meta learning, this enables us to fine-tune a high-quality text-to-speech model on just 30 minutes of data in a previously unseen language spoken by a previously unseen speaker.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 39 of its 68 references that are in the map. First posted on arXiv 7 Mar 2022.

Builds on

39 of 68 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  6. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  7. 2018VoxCeleb2: Deep Speaker Recognitioncited by 862
  8. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  9. 2017VoxCeleb: a large-scale speaker identification datasetcited by 714
  10. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  11. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 606
  12. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 555
27 more
  1. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  2. 2019Meta-Learning with Implicit Gradientscited by 523
  3. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 487
  4. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  5. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  6. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
  7. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  8. 2018How to train your MAMLcited by 306
  9. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 269
  10. 2020FastPitch: Parallel Text-to-speech with Pitch Predictioncited by 150
  11. 2017Deep Voice: Real-time Neural Text-to-Speechcited by 83
  12. 2020End-to-End Adversarial Text-to-Speechcited by 77
  13. 2019ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkitcited by 60
  14. 2017Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attentioncited by 57
  15. 2018Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytescited by 54
  16. 2019CSS10: A Collection of Single Speaker Speech Datasets for 10 Languagescited by 54
  17. 2021One TTS Alignment To Rule Them Allcited by 47
  18. 2020LRSpeech: Extremely Low-Resource Speech Synthesis and Recognitioncited by 43
  19. 2019End-to-end Text-to-speech for Low-resource Languages by Cross-Lingual Transfer Learningcited by 30
  20. 2021ESPnet2-TTS: Extending the Edge of TTS Researchcited by 22
  21. 2020Phonological Features for 0-shot Multilingual Speech Synthesiscited by 20
  22. 2018Fitting New Speakers Based on a Short Untranscribed Samplecited by 18
  23. 2018Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesiscited by 17
  24. 2021HUI-Audio-Corpus-German: A high quality TTS datasetcited by 14
  25. 2021Adapting TTS models For New Speakers using Transfer Learningcited by 12
  26. 2020Efficient neural speech synthesis for low-resource languages through multilingual modelingcited by 8
  27. 2019IMS-Speech: A Speech to Text Toolcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 7; 2024: 6; 2025: 2; 2026: 1.

20 papers.

Sort:

By area:

  1. 2022Low-Resource Multilingual and Zero-Shot Multispeaker TTScited by 15
  2. 2023AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representationcited by 14
  3. 2022Exact Prosody Cloning in Zero-Shot Multispeaker Text-to-Speechcited by 13
  4. 2024The Zeno's Paradox of `Low-Resource' Languagescited by 12
  5. 2023Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretrainingcited by 10
  6. 2024MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learningcited by 10
  7. 2022Speaker Anonymization with Phonetic Intermediate Representationscited by 9
  8. 2024Meta Learning Text-to-Speech Synthesis in over 7000 Languagescited by 9
  9. 2023The IMS Toucan System for the Blizzard Challenge 2023cited by 6
  10. 2022PoeticTTS -- Controllable Poetry Reading for Literary Studiescited by 5
  11. 2024Generating Feature Vectors from Phonetic Transcriptions in Cross-Linguistic Data Formatscited by 4
  12. 2025Voice Cloning: Comprehensive Surveycited by 4
8 more
  1. 2023CrossSpeech: Speaker-independent Acoustic Representation for Cross-lingual Speech Synthesiscited by 3
  2. 2023Strategies in Transfer Learning for Low-Resource Speech Synthesis: Phone Mapping, Features Input, and Source Language Selectioncited by 2
  3. 2025Investigating Stochastic Methods for Prosody Modeling in Speech Synthesiscited by 2
  4. 2023Controllable Generation of Artificial Speaker Embeddings through Discovery of Principal Directionscited by 1
  5. 2024HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworkscited by 1
  6. 2023The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speechcited by 0
  7. 2024CrossSpeech++: Cross-lingual Speech Synthesis with Decoupled Language and Speaker Generationcited by 0
  8. 2026Complex-Text Robustness Evaluation and Failure Diagnosis for Low-Resource Multilingual Text-to-Speechcited by 0