| 2 |
Towards Exploring Linguistic Variation in ASR Errors: Paradigm & Tool for Perceptual experiments
|
|
|
|
In: Proceedings of the New tools and methods for very-large-scale phonetics research workshop (VLSP'11) ; New tools and methods for very-large-scale phonetics research workshop (VLSP'11) ; https://hal.archives-ouvertes.fr/hal-01135133 ; New tools and methods for very-large-scale phonetics research workshop (VLSP'11), Jan 2011, Philadelphie, United States (2011)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Cross-lingual study of ASR errors: on the role of the context in human perception of near homophones
|
|
|
|
In: Proceedings of the 12th Annual Conference of the International Speech Communication Association (Interspeech'11) ; 12th Annual Conference of the International Speech Communication Association (Interspeech'11) ; https://hal.archives-ouvertes.fr/hal-01135150 ; 12th Annual Conference of the International Speech Communication Association (Interspeech'11), International Speech Communication Association (ISCA), Aug 2011, Florence, Italy. pp.1949--1952 (2011)
|
|
Abstract:
International audience ; It is widely acknowledged that human listeners significantly outperform machines when it comes to transcribing speech. This paper presents a paradigm for perceptual experiments that aims to increase our understanding of human and automatic speech recognition errors. The role of the context length is investigated through perceptual recovery of small homophonic words or near-homophones yielding frequent automatic transcription errors. The same experimental protocol of varied size speech stimuli transcription is applied to both French and English. Our hypothesis is that ambiguity due to homophonic words reduces with context size for both languages, which in turn should entail reduced perception and transcription errors. The results show that context plays a central role as the human word error rate decreases significantly with increasing context. The long-term aim is to improve the modelling of such ambiguous items to reduce automatic errors.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [SHS.LANGUE]Humanities and Social Sciences/Linguistics; automatic speech recognition errors; error analysis; function words; lexical context; linguistic variation; near-homophones; perceptual paradigm
|
|
URL: https://hal.archives-ouvertes.fr/hal-01135150
|
|
BASE
|
|
Hide details
|
|
|
| 4 |
Studying Luxembourgish phonetics via multilingual forced alignments
|
|
|
|
In: Proceedings of the 17th International Congress of Phonetic Sciences (ICPhS'11) ; 17th International Congress of Phonetic Sciences (ICPhS'11) ; https://hal.archives-ouvertes.fr/hal-01135124 ; 17th International Congress of Phonetic Sciences (ICPhS'11), Aug 2011, Hong Kong, China. pp.196-199 (2011)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Pronunciation and Writing Variants in an Under-Resourced Language: The Case of Luxembourgish Mobile N-Deletion
|
|
|
|
In: Human Language Technology. Challenges for Computer Science and Linguistics ; https://hal.archives-ouvertes.fr/hal-01135097 ; Zygmunt Vetulani. Human Language Technology. Challenges for Computer Science and Linguistics, 6562, Springer Berlin Heidelberg, pp.70-8-1, 2011, 4th Language and Technology Conference, LTC 2009, Poznan, Poland, November 6-8, 2009, Revised Selected Papers, 978-3-642-20094-6. ⟨10.1007/978-3-642-20095-3_7⟩ (2011)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Computational Modeling of Assimilated Speech: Cross-Linguistic Evidence
|
|
|
|
In: Snoeren, Natalie D.; & Gaskell, M. Gareth. (2007). Computational Modeling of Assimilated Speech: Cross-Linguistic Evidence. Proceedings of the Cognitive Science Society, 29(29). Retrieved from: http://www.escholarship.org/uc/item/2cd224tp (2007)
|
|
BASE
|
|
Show details
|
|
|
|
|
