Improving the performance of a Dutch CSR by modeling within-word and cross-word pronunciation variation

Autor: Judith M. Kessens, Mirjam Wester, Helmer Strik

Publikováno v: Speech Communication, 29, 193-207
Speech Communication, 29, 2-4, pp. 193-207

This article describes how the performance of a Dutch continuous speech recognizer was improved by modeling pronunciation variation. We propose a general procedure for modeling pronunciation variation. In short, it consists of adding pronunciation va

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::031c03bee42425b495653cbd8b0c580f
https://doi.org/10.1016/s0167-6393(99)00048-5

Results of the n-best 2008 dutch speech recognition evaluation

Autor: Judith M. Kessens, Henk van den Heuvel, David A. van Leeuwen, Eric Sanders

Publikováno v: INTERSPEECH

In this paper we report the results of a Dutch speech recognition system evaluation held in 2008. The evaluation contained material in two domains: Broadcast News (BN) and Conversational Telephone Speech (CTS) and in two main accent regions (Flemish

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::3479314b1d9e1e122225f1f0bb6d1868
https://doi.org/10.21437/interspeech.2009-677

User evaluation of a communication system that automatically generates captions to improve telephone communication

Autor: Adriana A. Zekveld, Sophia E. Kramer, Tammo Houtgast, Marcel S. M. G. Vlaming, Judith M. Kessens

Publikováno v: Zekveld, A A, Kramer, S E, Kessens, J M, Vlaming, M S M G & Houtgast, T 2009, ' User evaluation of a communication system that automatically generates captions to improve telephone communication ', Trends in Amplification, vol. 13, no. 1, pp. 44-68 . https://doi.org/10.1177/1084713808330207
Trends in Amplification, 13(1), 44-68. SAGE Publications Inc.
Trends in Amplification, 1, 13, 44-68

This study examined the subjective benefit obtained from automatically generated captions during telephone-speech comprehension in the presence of babble noise. Short stories were presented by telephone either with or without captions that were gener

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::33a1c45f616ea77d598093ad34bdd217
http://resolver.tudelft.nl/uuid:4143b910-332d-46c1-81d1-3347e5ccc564

The benefit obtained from visually displayed text from an automatic speech recognizer during listening to speech presented in noise

Autor: Sophia E. Kramer, Marcel S. M. G. Vlaming, Adriana A. Zekveld, Tammo Houtgast, Judith M. Kessens

Publikováno v: Ear and Hearing, 29(6), 838-852. LWW
Ear and Hearing, 6, 29, 838-852
Zekveld, A A, Kramer, S E, Kessens, J M, Vlaming, M S M G & Houtgast, T 2008, ' The benefit obtained from visually displayed text from an automatic speech recognizer during listening to speech presented in noise ', Ear and Hearing, vol. 29, no. 6, pp. 838-852 . https://doi.org/10.1097/AUD.0b013e31818005bd

OBJECTIVES: The aim of this study was to evaluate the benefit that listeners obtain from visually presented output from an automatic speech recognition (ASR) system during listening to speech in noise. DESIGN: Auditory-alone and audiovisual speech re

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6269edc3bc8e8a49294a34f656e0599c
http://resolver.tudelft.nl/uuid:26bcb0c3-888f-486e-9e42-dc02893427c3

On automatic phonetic transcription quality: Lower word error rates do not guarantee better transcriptions

Autor: Judith M. Kessens, Helmer Strik

Publikováno v: Computer Speech & Language, 18, 2, pp. 123-141
Computer Speech & Language, 18, 123-141

The first goal of this study was to investigate the effect of changing several properties of a continuous speech recognizer (CSR) on the automatic phonetic transcriptions generated by the same CSR. Our results show that the quality of the automatic t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f770b3a9e2037968d882933ae441bc7b
https://hdl.handle.net/2066/61813