The LIA Speech Recognition System: From 10xRT to 1xRT

Abstract : The LIA developed a speech recognition toolkit providing most of the components required by speech-to-text systems. This toolbox allowed to build a Broadcast News (BN) transcription system was involved in the ESTER evaluation campaign ([1]), on unconstrained transcription and real-time transcription tasks. In this paper, we describe the techniques we used to reach the real-time, starting from our baseline 10xRT system. We focus on some aspects of the A* search algorithm which are critical for both efficiency and accuracy. Then, we evaluate the impact of the different system components (lexicon, language models and acoustic models) to the trade-off between efficiency and accuracy. Experiments are carried out in framework of the ESTER evaluation campaign. Our results show that the real time system reaches performance on about 5.6% absolute WER whorses than the standard 10xRT system, with an absolute WER (Word Error Rate) of about 26.8%.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01318314
Contributor : Bibliothèque Universitaire Déposants Hal-Avignon <>
Submitted on : Thursday, May 19, 2016 - 2:33:14 PM
Last modification on : Tuesday, July 2, 2019 - 5:38:02 PM

Identifiers

  • HAL Id : hal-01318314, version 1

Collections

Citation

Georges Linarès, Pascal Nocera, D Massonié, Driss Matrouf. The LIA Speech Recognition System: From 10xRT to 1xRT. 10th International Conference, TSD, Sep 2007, Pilsen, Czech Republic. ⟨hal-01318314⟩

Share

Metrics

Record views

66