Skip to Main content Skip to Navigation
Conference papers

Effective keyword search for low-resourced conversational speech

Abstract : In this paper we aim to enhance keyword search for conversational telephone speech under low-resourced conditions. Two techniques to improve the detection of out-of-vocabulary keywords are assessed in this study: using extra text resources to augment the lexicon and language model, and via subword units for keyword search. Two approaches for data augmentation are explored to extend the limited amount of transcribed conversational speech: using conversational-like Web data and texts generated by recurrent neural networks. Contrastive comparisons of subword-based systems are performed to evaluate the benefits of multiple subword decodings and single decoding. Keyword search results are reported for all the techniques, but only some improve performance. Results are reported for the Mongolian and Igbo languages using data from the 2016 Babel program.
Complete list of metadata
Contributor : Antoine LAURENT Connect in order to contact the contributor
Submitted on : Tuesday, March 27, 2018 - 11:06:37 AM
Last modification on : Saturday, June 25, 2022 - 10:30:38 PM


  • HAL Id : hal-01744176, version 1


Rasa Lileikyte, Thiago Fraga-Silva, Lori Lamel, Jean-Luc Gauvain, Antoine Laurent, et al.. Effective keyword search for low-resourced conversational speech. icassp 2017, IEEE, Mar 2017, La Nouvelle Orléans, United States. ⟨hal-01744176⟩



Record views