mlsanityData to 7 Oct 2026

Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech

arXiv 2206.02147 ↗First posted 5 Jun 2022eess.AS cs.CL cs.SDcited by 0

Not on the map. Why?

Abstract (arXiv)

Polyphone disambiguation aims to capture accurate pronunciation knowledge from natural text sequences for reliable Text-to-speech (TTS) systems. However, previous approaches require substantial annotated training data and additional efforts from language experts, making it difficult to extend high-quality neural TTS systems to out-of-domain daily conversations and countless languages worldwide. This paper tackles the polyphone disambiguation problem from a concise and novel perspective: we propose Dict-TTS, a semantic-aware generative text-to-speech model with an online website dictionary (the existing prior information in the natural language). Specifically, we design a semantics-to-pronunciation attention (S2PA) module to match the semantic patterns between the input text sequence and the prior semantics in the dictionary and obtain the corresponding pronunciations; The S2PA module can be easily trained with the end-to-end TTS model without any annotated phoneme labels. Experimental results in three languages show that our model outperforms several strong baseline models in terms of pronunciation accuracy and improves the prosody modeling of TTS systems. Further extensive analyses demonstrate that each design in Dict-TTS is effective. The code is available at urlhttps://github.com/Zain-Jiang/Dict-TTS.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 80 references that are in the map. First posted on arXiv 5 Jun 2022.

Builds on

43 of 80 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  6. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  7. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  8. 2018Self-Attention with Relative Position Representationscited by 1,112
  9. 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,046
  10. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
  11. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  12. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
31 more
  1. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  2. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 555
  3. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 487
  4. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 269
  5. 2021WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognitioncited by 189
  6. 2021A Survey on Neural Speech Synthesiscited by 182
  7. 2021DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanismcited by 154
  8. 2018Dissecting Contextual Word Embeddings: Architecture and Representationcited by 146
  9. 2022FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesiscited by 136
  10. 2017Deep Voice: Real-time Neural Text-to-Speechcited by 83
  11. 2020End-to-End Adversarial Text-to-Speechcited by 77
  12. 2017JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesiscited by 57
  13. 2021PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTScited by 52
  14. 2021PortaSpeech: Portable and High-Quality Generative Text-to-Speechcited by 47
  15. 2020HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesiscited by 39
  16. 2021Lexicon Enhanced Chinese Sequence Labeling Using BERT Adaptercited by 34
  17. 2021Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modelingcited by 31
  18. 2019Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversioncited by 26
  19. 2021Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Taskscited by 22
  20. 2022GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speechcited by 21
  21. 2015Sequence-to-Sequence Neural Net Models for Grapheme-to-Phoneme Conversioncited by 19
  22. 2020Unified Mandarin TTS Front-end Based on Distilled BERT Modelcited by 18
  23. 2022SyntaSpeech: Syntax-Aware Generative Adversarial Text-to-Speechcited by 18
  24. 2020g2pM: A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Datasetcited by 15
  25. 2022Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speechcited by 13
  26. 2018Learning pronunciation from a foreign language in speech synthesis networkscited by 12
  27. 2019Polyphone Disambiguation for Mandarin Chinese Using Conditional Neural Network with Multi-level Embedding Featurescited by 8
  28. 2022g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarincited by 7
  29. 2022Polyphone disambiguation and accent prediction using pre-trained language models in Japanese TTS front-endcited by 5
  30. 2020Neural Machine Translation for Multilingual Grapheme-to-Phoneme Conversioncited by 4
  31. 2021Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledgecited by 3

Built on by

Not cited yet.