Morphosyntactic resources for automatic speech recognition

Stéphane Huet 1 Guillaume Gravier 1 Pascale Sébillot 1
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Texts generated by automatic speech recognition (ASR) systems have some specificities, related to the idiosyncrasies of oral productions or the principles of ASR systems, that make them more difficult to exploit than more conventional natural language written texts. This paper aims at studying the interest of morphosyntactic information as a useful resource for ASR. We show the ability of automatic methods to tag outputs of ASR systems, by obtaining a tag accuracy similar for automatic transcriptions to the 95-98 % usually reported for written texts, such as newspapers. We also demonstrate experimentally that tagging is useful to improve the quality of transcriptions by using morphosyntactic information in a post-processing stage of speech decoding. Indeed, we obtain a significant decrease of the word error rate with experiments done on French broadcast news from the ESTER corpus; we also notice an improvement of the sentence error rate and observe that a significant number of agreement errors are corrected.
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02021879
Contributor : Stéphane Huet <>
Submitted on : Saturday, February 16, 2019 - 9:07:51 PM
Last modification on : Wednesday, February 20, 2019 - 1:22:55 AM

File

LREC08.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02021879, version 1

Citation

Stéphane Huet, Guillaume Gravier, Pascale Sébillot. Morphosyntactic resources for automatic speech recognition. 6th International Conference on Language Resources and Evaluation (LREC), 2008, Marrakech, Morocco. ⟨hal-02021879⟩

Share

Metrics

Record views

23

Files downloads

21