HTEC: Human Transcription Error Correction

TL;DR

HTEC is a novel two-stage system for human transcription error correction that significantly improves transcription quality, surpasses human annotators, and effectively assists human transcribers as a co-pilot.

Contribution

This paper introduces HTEC, a new method combining error detection and sequence generation, with novel correction operations and phoneme-aware embeddings, outperforming existing approaches.

Findings

HTEC reduces WER by 2.2% to 4.5% compared to other methods.

HTEC improves transcription quality by 15.1% when used as a co-pilot.

HTEC surpasses human annotators in transcription accuracy.

Abstract

High-quality human transcription is essential for training and improving Automatic Speech Recognition (ASR) models. Recent study~\cite{libricrowd} has found that every 1% worse transcription Word Error Rate (WER) increases approximately 2% ASR WER by using the transcriptions to train ASR models. Transcription errors are inevitable for even highly-trained annotators. However, few studies have explored human transcription correction. Error correction methods for other problems, such as ASR error correction and grammatical error correction, do not perform sufficiently for this problem. Therefore, we propose HTEC for Human Transcription Error Correction. HTEC consists of two stages: Trans-Checker, an error detection model that predicts and masks erroneous words, and Trans-Filler, a sequence-to-sequence generative model that fills masked positions. We propose a holistic list of correction operations, including four novel operations handling deletion errors. We further propose a variant of embeddings that incorporates phoneme information into the input of the transformer. HTEC outperforms other methods by a large margin and surpasses human annotators by 2.2% to 4.5% in WER. Finally, we deployed HTEC to assist human annotators and showed HTEC is particularly effective as a co-pilot, which improves transcription quality by 15.1% without sacrificing transcription velocity.