Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, EpiSciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Skip to Main content Skip to Navigation

Mesures de confiance trame-synchrones et locales en reconnaissance automatique de la parole

Abstract : In automatic speech recognition, confidence measures aim at estimating the confidence we can give to a result (phone, word, sentence) provided by the speech recognition engine. In this thesis, we propose several confidence measures which are able to provide this estimation for applications using large vocabulary and on-the-fly recognition, as keyword indexation, broadcast news transcription, and live teaching class transcription for hard of hearing childs. We have defined two types of confidence measures. The first, based on likelihood ratio, are frame-synchronous measures which can be computed simultaneously with the recognition process of the sentence. The second ones are based on an estimation of the posterior probability limited to a local neighborhood of the considered word, and need only a short delay before being computed on the sub word graph extracted from the recognition process. These measures were assessed and compared to a state-of-the-art one, which is also based on posterior probability but which requires the recognition of the whole sentence. Two evaluations were performed on a real broadcast news corpus. The first one used the Equal Error Rate criterion in an automatic transcription task. The second evaluation was performed in a keyword spotting task. We achieved performance close to our reference measure with our local measures and a delay of less than one second. We also integrated one of our frame-synchronous measures in the decoding process of the recognition engine in order to improve the solution provided by the system and then to decrease the word error rate. We achieved to decrease the word error rate of around 1%.
Complete list of metadata
Contributor : Thèses UL Connect in order to contact the contributor
Submitted on : Thursday, March 29, 2018 - 11:29:23 AM
Last modification on : Saturday, October 16, 2021 - 11:26:08 AM
Long-term archiving on: : Thursday, September 13, 2018 - 8:51:38 PM


Files produced by the author(s)


  • HAL Id : tel-01748236, version 1



Joseph Razik. Mesures de confiance trame-synchrones et locales en reconnaissance automatique de la parole. Autre [cs.OH]. Université Henri Poincaré - Nancy 1, 2007. Français. ⟨NNT : 2007NAN10072⟩. ⟨tel-01748236⟩



Record views


Files downloads