mlsanityData to 7 Oct 2026

NeMo Inverse Text Normalization: From Development To Production

arXiv 2104.05055 ↗First posted 11 Apr 2021cs.CL cs.SD eess.AScited by 28

Not on the map. Why?

Abstract (arXiv)

Inverse text normalization (ITN) converts spoken-domain automatic speech recognition (ASR) output into written-domain text to improve the readability of the ASR output. Many state-of-the-art ITN systems use hand-written weighted finite-state transducer(WFST) grammars since this task has extremely low tolerance to unrecoverable errors. We introduce an open-source Python WFST-based library for ITN which enables a seamless path from development to production. We describe the specification of ITN grammar rules for English, but the library can be adapted for other languages. It can also be used for written-to-spoken text normalization. We evaluate the NeMo ITN library using a modified version of the Google Text normalization dataset.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 3 of its 16 references that are in the map. First posted on arXiv 11 Apr 2021.

Builds on

3 of 16 references.

References · 3

  1. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 230
  2. 2021Neural Inverse Text Normalizationcited by 19
  3. 2018Text normalization using memory augmented neural networkscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 3; 2024: 5; 2025: 7; 2026: 9.

28 papers.

Sort:

By area:

  1. 2024DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factorscited by 31
  2. 2023A Chat About Boring Problems: Studying GPT-based text normalizationcited by 10
  3. 2024On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Modelscited by 10
  4. 2025The Interspeech 2025 Speech Accessibility Project Challengecited by 9
  5. 2022Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalizationcited by 8
  6. 20241000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesiscited by 8
  7. 2024Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spottercited by 7
  8. 2021A Unified Transformer-based Framework for Duplex Text Normalizationcited by 6
  9. 2025SpeechWeave: Diverse Multilingual Synthetic Text & Audio Data Generation Pipeline for Training Text to Speech Modelscited by 5
  10. 2021Are E2E ASR models ready for an industrial usage?cited by 3
  11. 2022indic-punct: An automatic punctuation restoration and inverse text normalization framework for Indic languagescited by 3
  12. 2025Length-Aware Rotary Position Embedding for Text-Speech Alignmentcited by 2
16 more
  1. 2025SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech Systemcited by 1
  2. 2025Dynamic Context-Aware Streaming Pretrained Language Model For Inverse Text Normalizationcited by 1
  3. 2025Open Automatic Speech Recognition Models for Classical and Modern Standard Arabiccited by 1
  4. 2025The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialogue State Tracking Approachcited by 1
  5. 2026ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Modelscited by 1
  6. 2026SpokenUS: A Spoken User Simulator for Task-Oriented Dialoguecited by 1
  7. 2023OxfordVGG Submission to the EGO4D AV Transcription Challengecited by 0
  8. 2023Improving Robustness of Neural Inverse Text Normalization via Data-Augmentation, Semi-Supervised Learning, and Post-Aligning Methodcited by 0
  9. 2024Positional Description for Numerical Normalizationcited by 0
  10. 2026Sometin Beta Pass Notin: Improving Multilingual ASR for Nigerian Languages via Knowledge Distillationcited by 0
  11. 2026Earnings25: A Comprehensive 500-Hour Speech Benchmark for Financecited by 0
  12. 2026Dual-Form ASR: Semantics-Aware Inverse Text Normalization for Chinese Speech Recognitioncited by 0
  13. 2026The Hidden Cost of Digits: Number Normalization and WER in ASR Systemscited by 0
  14. 2026THA: Weighted Finite-State Text Normalization and Inverse Text Normalization for Khmercited by 0
  15. 2026Context Spanning: A Communication Framework for Full-Duplex Speech Models and External LLM Backendscited by 0
  16. 2026FuseAlign: Forced Alignment in the Wildcited by 0