Hybrid phonetic-neural model for correction in speech recognition systems

TL;DR

This paper presents a hybrid approach combining phonetic correction and deep neural networks to improve speech recognition accuracy in domain-specific applications, demonstrating reduced word error rates.

Contribution

It introduces a novel combination of phonetic correction algorithms with deep learning models for post-processing in speech recognition systems.

Findings

Reduced word error rate in transcriptions

Deep learning enhances phonetic correction effectiveness

Viability of hybrid models for domain-specific ASR

Abstract

Automatic speech recognition (ASR) is a relevant area in multiple settings because it provides a natural communication mechanism between applications and users. ASRs often fail in environments that use language specific to particular application domains. Some strategies have been explored to reduce errors in closed ASRs through post-processing, particularly automatic spell checking, and deep learning approaches. In this article, we explore using a deep neural network to refine the results of a phonetic correction algorithm applied to a telesales audio database. The results exhibit a reduction in the word error rate (WER), both in the original transcription and in the phonetic correction, which shows the viability of deep learning models together with post-processing correction strategies to reduce errors made by closed ASRs in specific language domains.