mlsanityData to 7 Oct 2026

Towards Building Text-To-Speech Systems for the Next Billion Users

arXiv 2211.09536 ↗First posted 17 Nov 2022cs.CL cs.LG cs.SDcited by 27

Not on the map. Why?

Abstract (arXiv)

Deep learning based text-to-speech (TTS) systems have been evolving rapidly with advances in model architectures, training methodologies, and generalization across speakers and languages. However, these advances have not been thoroughly investigated for Indian language speech synthesis. Such investigation is computationally expensive given the number and diversity of Indian languages, relatively lower resource availability, and the diverse set of advances in neural TTS that remain untested. In this paper, we evaluate the choice of acoustic models, vocoders, supplementary loss functions, training schedules, and speaker and language diversity for Dravidian and Indo-Aryan languages. Based on this, we identify monolingual models with FastPitch and HiFi-GAN V1, trained jointly on male and female speakers to perform the best. With this setup, we train and evaluate TTS models for 13 languages and find our models to significantly improve upon existing models in all languages as measured by mean opinion scores. We open-source all models on the Bhashini platform.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 17 Nov 2022.

Builds on

31 of 45 references.

References · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  3. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  4. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  5. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  6. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  7. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  8. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 555
  9. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 487
  10. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  11. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  12. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
19 more
  1. 2017Generalized End-to-End Loss for Speaker Verificationcited by 290
  2. 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 277
  3. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 269
  4. 2018Adversarial Audio Synthesiscited by 222
  5. 2021A Survey on Neural Speech Synthesiscited by 182
  6. 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speechcited by 156
  7. 2020FastPitch: Parallel Text-to-speech with Pitch Predictioncited by 150
  8. 2020DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancementcited by 133
  9. 2019High Fidelity Speech Synthesis with Adversarial Networkscited by 90
  10. 2017Deep Voice 2: Multi-Speaker Neural Text-to-Speechcited by 75
  11. 2017Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learningcited by 67
  12. 2020Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speechcited by 63
  13. 2021StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversioncited by 57
  14. 2021One TTS Alignment To Rule Them Allcited by 47
  15. 2021Towards Building ASR Systems for the Next Billion Userscited by 45
  16. 2022Revisiting Over-Smoothness in Text to Speechcited by 31
  17. 2019End-to-end Text-to-speech for Low-resource Languages by Cross-Lingual Transfer Learningcited by 30
  18. 2021Assessing Evaluation Metrics for Speech-to-Speech Translationcited by 10
  19. 2020Generic Indic Text-to-speech Synthesisers with Rapid Adaptation in an End-to-end Frameworkcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 8; 2025: 6; 2026: 11.

27 papers.

Sort:

By area:

  1. 2026OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Modelscited by 22
  2. 2024IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTScited by 15
  3. 2024Rethinking MUSHRA: Addressing Modern Challenges in Text-to-Speech Evaluationcited by 7
  4. 2024Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource Settingscited by 6
  5. 2025Parallel Corpora for Machine Translation in Low-resource Indic Languages: A Comprehensive Reviewcited by 4
  6. 2023Textless Speech-to-Speech Translation With Limited Parallel Datacited by 3
  7. 2024Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategiescited by 2
  8. 2024ELAICHI: Enhancing Low-resource TTS by Addressing Infrequent and Low-frequency Character Bigramscited by 2
  9. 2025Phir Hera Fairy: An English Fairytaler is a Strong Faker of Fluent Speech in Low-Resource Indian Languagescited by 2
  10. 2026Dialect Matters: Cross-Lingual ASR Transfer for Low-Resource Indic Language Varietiescited by 2
  11. 2024MunTTS: A Text-to-Speech System for Mundaricited by 1
  12. 2024Bahasa Harmony: A Comprehensive Dataset for Bahasa Text-to-Speech Synthesis with Discrete Codec Modeling of EnGen-TTScited by 1
15 more
  1. 2025Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper modelscited by 1
  2. 2026Dynamic Multi-Expert Projectors with Stabilized Routing for Multilingual Speech Recognitioncited by 1
  3. 2026Preferences of a Voice-First Nation: Large-Scale Pairwise Evaluation and Preference Analysis for TTS in Indian Languagescited by 1
  4. 2026Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Costcited by 1
  5. 2026PSP: An Interpretable Per-Dimension Accent Benchmark for Indic Text-to-Speechcited by 1
  6. 2023SALTTS: Leveraging Self-Supervised Speech Representations for improved Text-to-Speech Synthesiscited by 0
  7. 2024Enhancing Kurdish Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approachcited by 0
  8. 2025BnTTS: Few-Shot Speaker Adaptation in Low-Resource Settingcited by 0
  9. 2025Text to Speech System for Meitei Mayek Scriptcited by 0
  10. 2025Bhasha-Rupantarika: Algorithm-Hardware Co-design approach for Multilingual Neural Machine Translationcited by 0
  11. 2026Enhancing ASR Performance in the Medical Domain for Dravidian Languagescited by 0
  12. 2026Multilingual Multi-Speaker Unit Vocoders: A Systematic Analysis of Discrete Speech Representationscited by 0
  13. 2026Towards a Phonology-Informed Evaluation of Multilingual TTScited by 0
  14. 2026Domain-Specific Evaluation of Text-to-Speech Systems: A Multi-Metric Benchmarking Studycited by 0
  15. 2026BanglaKontho: Closing the Long-Form Gap in Bangla Text-to-Speechcited by 0