NeMo Inverse Text Normalization: From Development To Production

2021/04/11 by Yang Zhang, Evelina Bakhturina, Zhang, Yang +5 · 6 citations
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Natural Language Processing Techniques #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and dialogue systems #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2104.05055

openalex publication_date 2021/04/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Text normalization using memory augmented neural networks
• NeMo: a toolkit for building AI applications using Neural Modules

Cited by

• Earnings25: A Comprehensive 500-Hour Speech Benchmark for Finance
• FAC-FACodec: Controllable Zero-Shot Foreign Accent Conversion with Factorized Speech Codec
• The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialogue State Tracking Approach
• Hi-Fi Multi-Speaker English TTS Dataset
• SpeechWeave: Diverse Multilingual Synthetic Text & Audio Data Generation Pipeline for Training Text to Speech Models
• Length-Aware Rotary Position Embedding for Text-Speech Alignment
• The Interspeech 2025 Speech Accessibility Project Challenge

Related

• Improving Data Driven Inverse Text Normalization using Data Augmentation
• Neural Inverse Text Normalization
• Thutmose Tagger: Single-pass neural model for Inverse Text Normalization
• A Unified Transformer-based Framework for Duplex Text Normalization
• Language Agnostic Data-Driven Inverse Text Normalization