Morpho-Syntactic Study of Errors from Speech Recognition System
International audience The study provides an original standpoint of the speech transcription errors by focusing on the morpho-syntactic features of the erroneous chunks and of the surrounding left and right context. The typology concerns the forms, the lemmas and the POS involved in erroneous chunks...
Main Authors: | , , , |
---|---|
Other Authors: | , , |
Format: | Conference Object |
Language: | English |
Published: |
HAL CCSD
2014
|
Subjects: | |
Online Access: | https://hal.science/hal-01831243 |
id |
ftsorbonneuniv:oai:HAL:hal-01831243v1 |
---|---|
record_format |
openpolar |
spelling |
ftsorbonneuniv:oai:HAL:hal-01831243v1 2024-09-15T18:14:07+00:00 Morpho-Syntactic Study of Errors from Speech Recognition System Goryainova, Maria Grouin, Cyril Rosset, Sophie Vasilescu, Ioana Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI) Université Paris-Sud - Paris 11 (UP11)-Sorbonne Université - UFR d'Ingénierie (UFR 919) Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université Paris Saclay (COmUE) Reykjavik, Iceland 2014-01-01 https://hal.science/hal-01831243 en eng HAL CCSD hal-01831243 https://hal.science/hal-01831243 International Conference on Language Resources and Evaluation https://hal.science/hal-01831243 International Conference on Language Resources and Evaluation, Jan 2014, Reykjavik, Iceland Automatic Speech Recognition Error Analysis Morpho-Syntactic Analysis [INFO]Computer Science [cs] [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] info:eu-repo/semantics/conferenceObject Conference papers 2014 ftsorbonneuniv 2024-07-25T23:48:06Z International audience The study provides an original standpoint of the speech transcription errors by focusing on the morpho-syntactic features of the erroneous chunks and of the surrounding left and right context. The typology concerns the forms, the lemmas and the POS involved in erroneous chunks, and in the surrounding contexts. Comparison with error free contexts are also provided. The study is conducted on French. Morpho-syntactic analysis underlines that three main classes are particularly represented in the erroneous chunks: (i) grammatical words (to, of, the), (ii) auxiliary verbs (has, is), and (iii) modal verbs (should, must). Such items are widely encountered in the ASR outputs as frequent candidates to transcription errors. The analysis of the context points out that some left 3-grams contexts (e.g., repetitions, that is disfluencies, bracketing formulas such as cest, etc.) may be better predictors than others. Finally, the surface analysis conducted through a Levensthein distance analysis, highlighted that the most common distance is of 2 characters and mainly involves differences between inflected forms of a unique item. Conference Object Iceland HAL Sorbonne Université |
institution |
Open Polar |
collection |
HAL Sorbonne Université |
op_collection_id |
ftsorbonneuniv |
language |
English |
topic |
Automatic Speech Recognition Error Analysis Morpho-Syntactic Analysis [INFO]Computer Science [cs] [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] |
spellingShingle |
Automatic Speech Recognition Error Analysis Morpho-Syntactic Analysis [INFO]Computer Science [cs] [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] Goryainova, Maria Grouin, Cyril Rosset, Sophie Vasilescu, Ioana Morpho-Syntactic Study of Errors from Speech Recognition System |
topic_facet |
Automatic Speech Recognition Error Analysis Morpho-Syntactic Analysis [INFO]Computer Science [cs] [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] |
description |
International audience The study provides an original standpoint of the speech transcription errors by focusing on the morpho-syntactic features of the erroneous chunks and of the surrounding left and right context. The typology concerns the forms, the lemmas and the POS involved in erroneous chunks, and in the surrounding contexts. Comparison with error free contexts are also provided. The study is conducted on French. Morpho-syntactic analysis underlines that three main classes are particularly represented in the erroneous chunks: (i) grammatical words (to, of, the), (ii) auxiliary verbs (has, is), and (iii) modal verbs (should, must). Such items are widely encountered in the ASR outputs as frequent candidates to transcription errors. The analysis of the context points out that some left 3-grams contexts (e.g., repetitions, that is disfluencies, bracketing formulas such as cest, etc.) may be better predictors than others. Finally, the surface analysis conducted through a Levensthein distance analysis, highlighted that the most common distance is of 2 characters and mainly involves differences between inflected forms of a unique item. |
author2 |
Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI) Université Paris-Sud - Paris 11 (UP11)-Sorbonne Université - UFR d'Ingénierie (UFR 919) Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université Paris Saclay (COmUE) |
format |
Conference Object |
author |
Goryainova, Maria Grouin, Cyril Rosset, Sophie Vasilescu, Ioana |
author_facet |
Goryainova, Maria Grouin, Cyril Rosset, Sophie Vasilescu, Ioana |
author_sort |
Goryainova, Maria |
title |
Morpho-Syntactic Study of Errors from Speech Recognition System |
title_short |
Morpho-Syntactic Study of Errors from Speech Recognition System |
title_full |
Morpho-Syntactic Study of Errors from Speech Recognition System |
title_fullStr |
Morpho-Syntactic Study of Errors from Speech Recognition System |
title_full_unstemmed |
Morpho-Syntactic Study of Errors from Speech Recognition System |
title_sort |
morpho-syntactic study of errors from speech recognition system |
publisher |
HAL CCSD |
publishDate |
2014 |
url |
https://hal.science/hal-01831243 |
op_coverage |
Reykjavik, Iceland |
genre |
Iceland |
genre_facet |
Iceland |
op_source |
International Conference on Language Resources and Evaluation https://hal.science/hal-01831243 International Conference on Language Resources and Evaluation, Jan 2014, Reykjavik, Iceland |
op_relation |
hal-01831243 https://hal.science/hal-01831243 |
_version_ |
1810451898646396928 |