Is Syllable Stress Information Robust for ASR in Adverse Conditions?

Bogdan Ludusan 1 Stefan Ziegler 2 Guillaume Gravier 3
2 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
3 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : This paper presents a study on the robustness of stress information for automatic speech recognition in the presence of noise. The syllable stress, extracted from the speech signal, was integrated in the recognition process by means of a previously proposed decoding method. Experiments were conducted for several signal-to-noise ratio conditions and the results show that stress information is robust in the presence of medium to low noise. This was found to be true both when syllable boundary information was used for stress detection and when this information was not available. Furthermore, the obtained relative improvement increased with a decrease in signal quality, indicating that the stressed parts of the signal can be considered islands of reliability.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01026423
Contributor : Guillaume Gravier <>
Submitted on : Monday, July 21, 2014 - 3:48:03 PM
Last modification on : Thursday, December 6, 2018 - 1:53:32 AM

Identifiers

  • HAL Id : hal-01026423, version 1

Citation

Bogdan Ludusan, Stefan Ziegler, Guillaume Gravier. Is Syllable Stress Information Robust for ASR in Adverse Conditions?. International Conference on Speech Prosody, May 2014, Dublin, Ireland. pp.939-943. ⟨hal-01026423⟩

Share

Metrics

Record views

1052