Analysis of Speech Recognition Systems and Error Correction Approaches

Author (Your Name)

Saki ImaiFollow

Date of Award

2024

Document Type

Honors Thesis (Open Access)

Department

Colby College. Computer Science Dept.

Advisor(s)

Amanda Stent

Second Advisor

Tahiya Chowdhury

Abstract

Despite significant advances in automatic speech recognition (ASR) accuracy, challenges remain. Naturally occurring conversation often involves multiple overlapping speakers, of different ages, accents and genders, as well as noisy environments and suboptimal audio recording equipment, all of which reduce ASR accuracy. In this study, we evaluate the accuracy of state of the art open source ASR systems across diverse conversational speech datasets, examining the impact of audio and speaker characteristics on WER. We then explore the potential of ASR ensembling plus post-ASR correction methods to improve transcription accuracy. Our findings underscore the need for robust error correction techniques and of continuing to address demographic biases to enhance ASR performance and inclusivity.

Keywords

speech recognition

Recommended Citation