Integrating Stress Information in Large Vocabulary Continuous Speech Recognition

Bogdan Ludusan 1 Stefan Ziegler 2 Guillaume Gravier 1
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
2 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : In this paper we propose a novel method for integrating stress information in the decoding step of a speech recognizer. A multiscale rhythm model was used to determine the stress scores for each syllable, which are further used to reinforce paths during search. Two strategies for integrating the stress were employed: the first one reinforces paths through all the syllables with a value proportional to the their stress score, while the second one enhances paths passing only through stressed syllables, but with a constant value. The former strategy slightly outperforms the later, bringing a relative improvement of more than 2% over the baseline. Furthermore, the stress information proved to be a robust feature, by performing well even for foreign-accented speech.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [12 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00758622
Contributor : Guillaume Gravier <>
Submitted on : Thursday, November 29, 2012 - 9:23:36 AM
Last modification on : Friday, November 16, 2018 - 1:23:47 AM
Document(s) archivé(s) le : Saturday, December 17, 2016 - 5:47:00 PM

File

IS2012_stress.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00758622, version 1

Citation

Bogdan Ludusan, Stefan Ziegler, Guillaume Gravier. Integrating Stress Information in Large Vocabulary Continuous Speech Recognition. INTERSPEECH - Annual Conference of the International Speech Communication Association, 2012, United States. ⟨hal-00758622⟩

Share

Metrics

Record views

980

Files downloads

209