Boosting bonsai trees for efficient features combination : application to speaker role identification

Abstract : In this article, we tackle the problem of speaker role detection from broadcast news shows. In the literature, many proposed solutions are based on the combination of various features coming from acoustic, lexical and semantic information with a machine learning algorithm. Many previous studies mention the use of boosting over decision stumps to combine efficiently these features. In this work, we propose a modification of this state-of-the-art machine learning algorithm changing the weak learner (decision stumps) by small decision trees, denoted bonsai trees. Experiments show that using bonsai trees as weak learners for the boosting algorithm largely improves both system error rate and learning time.
Liste complète des métadonnées

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/hal-01025171
Contributor : Christian Raymond <>
Submitted on : Thursday, July 17, 2014 - 11:32:35 AM
Last modification on : Monday, March 18, 2019 - 4:23:32 PM
Document(s) archivé(s) le : Monday, November 24, 2014 - 5:26:54 PM

File

interspeech2014.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01025171, version 1

Citation

Antoine Laurent, Nathalie Camelin, Christian Raymond. Boosting bonsai trees for efficient features combination : application to speaker role identification. Interspeech, Sep 2014, Singapour, Singapore. ⟨hal-01025171⟩

Share

Metrics

Record views

735

Files downloads

418