Phoneme Similarity Matrices to Improve Long Audio Alignment for Automatic Subtitling
International audience Long audio alignment systems for Spanish and English are presented, within an automatic subtitling application. Language-specific phone decoders automatically recognize audio contents at phoneme level. At the same time, language-dependent grapheme-to-phoneme modules perform a...
Main Authors: | , , |
---|---|
Other Authors: | , , , , , |
Format: | Conference Object |
Language: | English |
Published: |
HAL CCSD
2014
|
Subjects: | |
Online Access: | https://hal.archives-ouvertes.fr/hal-01099239 https://hal.archives-ouvertes.fr/hal-01099239/document https://hal.archives-ouvertes.fr/hal-01099239/file/387_Paper.pdf |
id |
ftccsdartic:oai:HAL:hal-01099239v1 |
---|---|
record_format |
openpolar |
spelling |
ftccsdartic:oai:HAL:hal-01099239v1 2023-05-15T16:50:07+02:00 Phoneme Similarity Matrices to Improve Long Audio Alignment for Automatic Subtitling Ruiz, Pablo Álvarez, Aitor Arzelus, Haritz Lattice - Langues, Textes, Traitements informatiques, Cognition - UMR 8094 (Lattice) Département Littératures et langage (LILA) École normale supérieure - Paris (ENS Paris) Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-École normale supérieure - Paris (ENS Paris) Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Université Sorbonne Paris Cité (USPC)-Université Sorbonne Nouvelle - Paris 3 VicomTech Reykjavik, Iceland 2014-05 https://hal.archives-ouvertes.fr/hal-01099239 https://hal.archives-ouvertes.fr/hal-01099239/document https://hal.archives-ouvertes.fr/hal-01099239/file/387_Paper.pdf en eng HAL CCSD hal-01099239 https://hal.archives-ouvertes.fr/hal-01099239 https://hal.archives-ouvertes.fr/hal-01099239/document https://hal.archives-ouvertes.fr/hal-01099239/file/387_Paper.pdf info:eu-repo/semantics/OpenAccess LREC, Ninth International Conference on Language Resources and Evaluation https://hal.archives-ouvertes.fr/hal-01099239 LREC, Ninth International Conference on Language Resources and Evaluation, May 2014, Reykjavik, Iceland http://lrec2014.lrec-conf.org/en/ automatic subtitling long audio alignment phoneme similarity matrices [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] [SHS.LANGUE]Humanities and Social Sciences/Linguistics info:eu-repo/semantics/conferenceObject Conference papers 2014 ftccsdartic 2021-12-05T03:13:17Z International audience Long audio alignment systems for Spanish and English are presented, within an automatic subtitling application. Language-specific phone decoders automatically recognize audio contents at phoneme level. At the same time, language-dependent grapheme-to-phoneme modules perform a transcription of the script for the audio. A dynamic programming algorithm (Hirschberg's algorithm) finds matches between the phonemes automatically recognized by the phone decoder and the phonemes in the script's transcription. Alignment accuracy is evaluated when scoring alignment operations with a baseline binary matrix, and when scoring alignment operations with several continuous-score matrices, based on phoneme similarity as assessed through comparing multivalued phonological features. Alignment accuracy results are reported at phoneme, word and subtitle level. Alignment accuracy when using the continuous scoring matrices based on phonological similarity was clearly higher than when using the baseline binary matrix. Conference Object Iceland Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) |
institution |
Open Polar |
collection |
Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) |
op_collection_id |
ftccsdartic |
language |
English |
topic |
automatic subtitling long audio alignment phoneme similarity matrices [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] [SHS.LANGUE]Humanities and Social Sciences/Linguistics |
spellingShingle |
automatic subtitling long audio alignment phoneme similarity matrices [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] [SHS.LANGUE]Humanities and Social Sciences/Linguistics Ruiz, Pablo Álvarez, Aitor Arzelus, Haritz Phoneme Similarity Matrices to Improve Long Audio Alignment for Automatic Subtitling |
topic_facet |
automatic subtitling long audio alignment phoneme similarity matrices [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] [SHS.LANGUE]Humanities and Social Sciences/Linguistics |
description |
International audience Long audio alignment systems for Spanish and English are presented, within an automatic subtitling application. Language-specific phone decoders automatically recognize audio contents at phoneme level. At the same time, language-dependent grapheme-to-phoneme modules perform a transcription of the script for the audio. A dynamic programming algorithm (Hirschberg's algorithm) finds matches between the phonemes automatically recognized by the phone decoder and the phonemes in the script's transcription. Alignment accuracy is evaluated when scoring alignment operations with a baseline binary matrix, and when scoring alignment operations with several continuous-score matrices, based on phoneme similarity as assessed through comparing multivalued phonological features. Alignment accuracy results are reported at phoneme, word and subtitle level. Alignment accuracy when using the continuous scoring matrices based on phonological similarity was clearly higher than when using the baseline binary matrix. |
author2 |
Lattice - Langues, Textes, Traitements informatiques, Cognition - UMR 8094 (Lattice) Département Littératures et langage (LILA) École normale supérieure - Paris (ENS Paris) Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-École normale supérieure - Paris (ENS Paris) Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Université Sorbonne Paris Cité (USPC)-Université Sorbonne Nouvelle - Paris 3 VicomTech |
format |
Conference Object |
author |
Ruiz, Pablo Álvarez, Aitor Arzelus, Haritz |
author_facet |
Ruiz, Pablo Álvarez, Aitor Arzelus, Haritz |
author_sort |
Ruiz, Pablo |
title |
Phoneme Similarity Matrices to Improve Long Audio Alignment for Automatic Subtitling |
title_short |
Phoneme Similarity Matrices to Improve Long Audio Alignment for Automatic Subtitling |
title_full |
Phoneme Similarity Matrices to Improve Long Audio Alignment for Automatic Subtitling |
title_fullStr |
Phoneme Similarity Matrices to Improve Long Audio Alignment for Automatic Subtitling |
title_full_unstemmed |
Phoneme Similarity Matrices to Improve Long Audio Alignment for Automatic Subtitling |
title_sort |
phoneme similarity matrices to improve long audio alignment for automatic subtitling |
publisher |
HAL CCSD |
publishDate |
2014 |
url |
https://hal.archives-ouvertes.fr/hal-01099239 https://hal.archives-ouvertes.fr/hal-01099239/document https://hal.archives-ouvertes.fr/hal-01099239/file/387_Paper.pdf |
op_coverage |
Reykjavik, Iceland |
genre |
Iceland |
genre_facet |
Iceland |
op_source |
LREC, Ninth International Conference on Language Resources and Evaluation https://hal.archives-ouvertes.fr/hal-01099239 LREC, Ninth International Conference on Language Resources and Evaluation, May 2014, Reykjavik, Iceland http://lrec2014.lrec-conf.org/en/ |
op_relation |
hal-01099239 https://hal.archives-ouvertes.fr/hal-01099239 https://hal.archives-ouvertes.fr/hal-01099239/document https://hal.archives-ouvertes.fr/hal-01099239/file/387_Paper.pdf |
op_rights |
info:eu-repo/semantics/OpenAccess |
_version_ |
1766040297078259712 |