Towards a new speech event detection approach for landmark-based speech recognition

Stefan Ziegler 1 Bogdan Ludusan 2 Guillaume Gravier 2
1 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
2 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : In this work, we present a new approach for the classification and detection of speech units for the use in landmark or eventbased speech recognition systems. We use segmentation to model any time-variable speech unit by a fixed-dimensional observation vector, in order to train a committee of boosted decision stumps on labeled training data. Given an unknown speech signal, the presence of a desired speech unit is estimated by searching for each time frame the corresponding segment, that provides the maximum classification score. This approach improves the accuracy of a phoneme classification task by 1.7%, compared to classification using HMMs. Applying this approach to the detection of broad phonetic landmarks inside a landmark-driven HMM-based speech recognizer significantly improves speech recognition.
Document type :
Conference papers
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00758424
Contributor : Guillaume Gravier <>
Submitted on : Wednesday, November 28, 2012 - 4:58:12 PM
Last modification on : Friday, November 16, 2018 - 1:21:48 AM
Long-term archiving on : Saturday, December 17, 2016 - 5:28:41 PM

File

slt8_final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00758424, version 1

Citation

Stefan Ziegler, Bogdan Ludusan, Guillaume Gravier. Towards a new speech event detection approach for landmark-based speech recognition. SLT - Workshop on Spoken Language Technology, 2012, United States. ⟨hal-00758424⟩

Share

Metrics

Record views

1077

Files downloads

326