On the Effects of Automatic Transcription and Segmentation Errors in Hungarian Spoken Language Processing

  • Máté Ákos Tündik Department of Telecommunication and Media Informatics, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, H-1117 Budapest, Magyar tudósok körútja 2., Hungary; Nokia Solutions and Networks Ltd., 1083 Budapest, Bókay János u. 36-42, Hungary
  • Valér Kaszás Department of Telecommunication and Media Informatics, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, H-1117 Budapest, Magyar tudósok körútja 2., Hungary
  • György Szaszák Department of Telecommunication and Media Informatics, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, H-1117 Budapest, Magyar tudósok körútja 2., Hungary

Abstract

Emerging Artificial Intelligence (AI) technology has brought machines to reach an equal or even superior level compared to human capabilities in several fields; nevertheless, among many other fields, making a computer able to understand human language still remains a challenge. When dealing with speech understanding, Automatic Speech Recognition (ASR) is used to generate transcripts, which are processed with text-based tools targeting Spoken Language Understanding (SLU). Depending on the ASR quality (which further depends on speech quality, the complexity of the topic, environment etc.), transcripts contain errors, which propagate further into the processing pipeline. Subjective tests show on the other hand, that humans understand quite well ASR-closed captions, despite the word and punctuation errors. Through word embedding based semantic parsing, the present paper is interested in quantifying the semantic bias introduced by ASR error propagation. As a special use case, speech summarization is also evaluated with regard to ASR error propagation. We show, that despite the higher word error rates seen with the highly inflectional Hungarian, the semantic space suffers least impact than the difference in Word Error Rate would suggest.

Keywords: automatic punctuation, word embedding, semantic similarity, automatic summarization, speech recognition
Published online
2019-06-13
How to Cite
Tündik, M. Ákos, Kaszás, V. and Szaszák, G. “On the Effects of Automatic Transcription and Segmentation Errors in Hungarian Spoken Language Processing”, Periodica Polytechnica Electrical Engineering and Computer Science. doi: https://doi.org/10.3311/PPee.14052.
Section
Articles