How good are humans at recognizing Flemish speech compared to AI-based automatic speech recognizers?
R. Popa (TU Delft - Electrical Engineering, Mathematics and Computer Science)
O.E. Scharenborg – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Y. Zhang – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)
B.J.W. Dudzik – Graduation committee member (TU Delft - Electrical Engineering, Mathematics and Computer Science)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Automatic Speech Recognizers (ASR) transcribe speech to text and have become very popular. These systems need to accommodate all types of speech, and problems appear for different genders, ages and regional accents. In this paper we aim to discover what are the differences in types of recognition errors made by Dutch listeners and ASR systems in transcribing Flemish Dutch speech. This has been done through an experiment where human listeners and ASRs listened to 40 audio samples coming from speakers from different regions. Afterwards the transcriptions were collected, processed and we calculated the word error rate (WER). ASRs outperformed humans, scored lower WER, with differences appearing based on speaker region. Results show that ASR systems display similar recognition error patterns, a lot of substitutions and deletions, and very few insertions. The main difference stands in the way humans and ASRs deal with confusing audio. Humans tend to use similar words that fit the context whereas ASRs are more prone to inserting unrelated words.