Four-in-One: A Joint Approach to Inverse Text Normalization, Punctuation, Capitalization, and Disfluency for Automatic Speech Recognition

TL;DR

This paper introduces a unified transformer-based model that jointly handles inverse text normalization, punctuation, capitalization, and disfluency correction in speech-to-text conversion, improving efficiency and performance.

Contribution

It presents a novel joint approach using a single transformer model to perform multiple formatting tasks simultaneously, outperforming task-specific models.

Findings

Unified model matches or exceeds task-specific models.

Effective across multiple domains and benchmark datasets.

Simplifies speech-to-text formatting pipeline.

Abstract

Features such as punctuation, capitalization, and formatting of entities are important for readability, understanding, and natural language processing tasks. However, Automatic Speech Recognition (ASR) systems produce spoken-form text devoid of formatting, and tagging approaches to formatting address just one or two features at a time. In this paper, we unify spoken-to-written text conversion via a two-stage process: First, we use a single transformer tagging model to jointly produce token-level tags for inverse text normalization (ITN), punctuation, capitalization, and disfluencies. Then, we apply the tags to generate written-form text and use weighted finite state transducer (WFST) grammars to format tagged ITN entity spans. Despite joining four models into one, our unified tagging approach matches or outperforms task-specific models across all four tasks on benchmark test sets across several domains.