Analysis of Phonetic Transcriptions for Danish Automatic Speech Recognition

Andreas Søeborg Kirkedal

Analysis of Phonetic Transcriptions for Danish Automatic Speech Recognition

Andreas Søeborg Kirkedal

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

Abstrakt

Automatic speech recognition (ASR) relies on three resources: audio, orthographic transcriptions and a pronunciation dictionary. The dictionary or lexicon maps orthographic words to sequences of phones or phonemes that represent the pronunciation of the corresponding word. The quality of a speech recognition system depends heavily on the dictionary and the transcriptions therein. This paper presents an analysis of phonetic/phonemic features that are salient for current Danish ASR systems. This preliminary study consists of a series of experiments using an ASR system trained on the DK-PAROLE corpus. The analysis indicates that transcribing e.g. stress or vowel duration has a negative impact on performance. The best performance is obtained with coarse phonetic annotation and improves performance 1% word error rate and 3.8% sentence error rate.

Originalsprog	Engelsk
Titel	Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013)
Redaktører	Stephan Oepen, Kristin Hagen, Janne Bondi Johannessen
Udgivelsessted	Linköping
Forlag	Linköping University Electronic Press
Publikationsdato	2013
Sider	321-330
ISBN (Trykt)	9789175195896
Status	Udgivet - 2013
Begivenhed	NODALIDA 2013: The 19th Nordic Conference of Computational Linguistics - University of Oslo, Oslo, Norge Varighed: 22 maj 2013 → 24 maj 2013 Konferencens nummer: 19 http://www.hf.uio.no/iln/english/research/news-and-events/events/conferences/2013/nodalida/index.html

Konference

Konference	NODALIDA 2013
Nummer	19
Lokation	University of Oslo
Land	Norge
By	Oslo
Periode	22/05/2013 → 24/05/2013
Internetadresse	http://www.hf.uio.no/iln/english/research/news-and-events/events/conferences/2013/nodalida/index.html

Navn	NEALT (Northern European Association of Language Technology) Proceedings Series
Vol/bind	16
ISSN	1736-6305

Emneord

Automatic speech recognition
Phonetics
Phonology
Speech
Phonetic transcription

Adgang til dokumentet

http://www.ep.liu.se/ecp_home/index.en.aspx?issue=085

Citationsformater

Kirkedal, A. S. (2013). Analysis of Phonetic Transcriptions for Danish Automatic Speech Recognition. I S. Oepen, K. Hagen, & J. B. Johannessen (red.), Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013) (s. 321-330). Linköping University Electronic Press. NEALT (Northern European Association of Language Technology) Proceedings Series Bind 16 http://www.ep.liu.se/ecp_home/index.en.aspx?issue=085

Kirkedal, Andreas Søeborg. / Analysis of Phonetic Transcriptions for Danish Automatic Speech Recognition. Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013). red. / Stephan Oepen ; Kristin Hagen ; Janne Bondi Johannessen. Linköping : Linköping University Electronic Press, 2013. s. 321-330 (NEALT (Northern European Association of Language Technology) Proceedings Series, Bind 16).

@inproceedings{29d081897a824b018104d4fc871eb849,

title = "Analysis of Phonetic Transcriptions for Danish Automatic Speech Recognition",

abstract = "Automatic speech recognition (ASR) relies on three resources: audio, orthographic transcriptions and a pronunciation dictionary. The dictionary or lexicon maps orthographic words to sequences of phones or phonemes that represent the pronunciation of the corresponding word. The quality of a speech recognition system depends heavily on the dictionary and the transcriptions therein. This paper presents an analysis of phonetic/phonemic features that are salient for current Danish ASR systems. This preliminary study consists of a series of experiments using an ASR system trained on the DK-PAROLE corpus. The analysis indicates that transcribing e.g. stress or vowel duration has a negative impact on performance. The best performance is obtained with coarse phonetic annotation and improves performance 1% word error rate and 3.8% sentence error rate.",

keywords = "Automatic speech recognition, Phonetics, Phonology, Speech, Phonetic transcription",

author = "Kirkedal, {Andreas S{\o}eborg}",

year = "2013",

language = "English",

isbn = "9789175195896",

series = "NEALT (Northern European Association of Language Technology) Proceedings Series",

pages = "321--330",

editor = "Oepen, {Stephan } and Hagen, {Kristin } and Johannessen, {Janne Bondi }",

booktitle = "Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013)",

publisher = "Link{\"o}ping University Electronic Press",

address = "Sweden",

note = "null ; Conference date: 22-05-2013 Through 24-05-2013",

url = "http://www.hf.uio.no/iln/english/research/news-and-events/events/conferences/2013/nodalida/index.html",

}

Kirkedal, AS 2013, Analysis of Phonetic Transcriptions for Danish Automatic Speech Recognition. i S Oepen, K Hagen & JB Johannessen (red), Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013). Linköping University Electronic Press, Linköping, NEALT (Northern European Association of Language Technology) Proceedings Series, bind 16, s. 321-330, NODALIDA 2013, Oslo, Norge, 22/05/2013. <http://www.ep.liu.se/ecp_home/index.en.aspx?issue=085>

Analysis of Phonetic Transcriptions for Danish Automatic Speech Recognition. / Kirkedal, Andreas Søeborg.

Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013). red. / Stephan Oepen; Kristin Hagen; Janne Bondi Johannessen. Linköping : Linköping University Electronic Press, 2013. s. 321-330 (NEALT (Northern European Association of Language Technology) Proceedings Series, Bind 16).

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - Analysis of Phonetic Transcriptions for Danish Automatic Speech Recognition

AU - Kirkedal, Andreas Søeborg

N1 - Conference code: 19

PY - 2013

Y1 - 2013

N2 - Automatic speech recognition (ASR) relies on three resources: audio, orthographic transcriptions and a pronunciation dictionary. The dictionary or lexicon maps orthographic words to sequences of phones or phonemes that represent the pronunciation of the corresponding word. The quality of a speech recognition system depends heavily on the dictionary and the transcriptions therein. This paper presents an analysis of phonetic/phonemic features that are salient for current Danish ASR systems. This preliminary study consists of a series of experiments using an ASR system trained on the DK-PAROLE corpus. The analysis indicates that transcribing e.g. stress or vowel duration has a negative impact on performance. The best performance is obtained with coarse phonetic annotation and improves performance 1% word error rate and 3.8% sentence error rate.

AB - Automatic speech recognition (ASR) relies on three resources: audio, orthographic transcriptions and a pronunciation dictionary. The dictionary or lexicon maps orthographic words to sequences of phones or phonemes that represent the pronunciation of the corresponding word. The quality of a speech recognition system depends heavily on the dictionary and the transcriptions therein. This paper presents an analysis of phonetic/phonemic features that are salient for current Danish ASR systems. This preliminary study consists of a series of experiments using an ASR system trained on the DK-PAROLE corpus. The analysis indicates that transcribing e.g. stress or vowel duration has a negative impact on performance. The best performance is obtained with coarse phonetic annotation and improves performance 1% word error rate and 3.8% sentence error rate.

KW - Automatic speech recognition

KW - Phonetics

KW - Phonology

KW - Speech

KW - Phonetic transcription

M3 - Article in proceedings

SN - 9789175195896

T3 - NEALT (Northern European Association of Language Technology) Proceedings Series

SP - 321

EP - 330

BT - Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013)

A2 - Oepen, Stephan

A2 - Hagen, Kristin

A2 - Johannessen, Janne Bondi

PB - Linköping University Electronic Press

CY - Linköping

Y2 - 22 May 2013 through 24 May 2013

ER -

Kirkedal AS. Analysis of Phonetic Transcriptions for Danish Automatic Speech Recognition. I Oepen S, Hagen K, Johannessen JB, red., Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013). Linköping: Linköping University Electronic Press. 2013. s. 321-330. (NEALT (Northern European Association of Language Technology) Proceedings Series, Bind 16).