Post-Editing Error Correction Algorithm for Speech Recognition using Bing Spelling Suggestion

TL;DR

This paper introduces a post-editing error correction algorithm for speech recognition that leverages Bing's spelling suggestion to improve transcription accuracy, especially in low-quality input scenarios.

Contribution

The paper presents a novel approach using Bing's online spelling suggestion to correct ASR errors through token-based spell checking and correction.

Findings

Significant reduction in ASR errors observed

Improved overall error correction rate

Effective across multiple languages

Abstract

ASR short for Automatic Speech Recognition is the process of converting a spoken speech into text that can be manipulated by a computer. Although ASR has several applications, it is still erroneous and imprecise especially if used in a harsh surrounding wherein the input speech is of low quality. This paper proposes a post-editing ASR error correction method and algorithm based on Bing's online spelling suggestion. In this approach, the ASR recognized output text is spell-checked using Bing's spelling suggestion technology to detect and correct misrecognized words. More specifically, the proposed algorithm breaks down the ASR output text into several word-tokens that are submitted as search queries to Bing search engine. A returned spelling suggestion implies that a query is misspelled; and thus it is replaced by the suggested correction; otherwise, no correction is performed and the algorithm continues with the next token until all tokens get validated. Experiments carried out on various speeches in different languages indicated a successful decrease in the number of ASR errors and an improvement in the overall error correction rate. Future research can improve upon the proposed algorithm so much so that it can be parallelized to take advantage of multiprocessor computers.