A Comparison of Normalization Techniques Applied to Latent Space Representations for Speech Analytics - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

A Comparison of Normalization Techniques Applied to Latent Space Representations for Speech Analytics

Mohamed Morchid
Richard Dufour
Driss Matrouf

Abstract

In the context of noisy environments, Automatic Speech Recognition (ASR) systems usually produce poor transcription quality which also negatively impact performance of speech analyt-ics. Various methods have then been proposed to compensate the bad effect of ASR errors, mainly by projecting transcribed words in an abstract space. In this paper, we seek to identify themes from dialogues of telephone conversation services using latent topic-spaces estimated from a latent Dirichlet allocation (LDA). As an outcome, a document can be represented with a vector containing probabilities to be associated to each topic estimated with LDA. This vector should nonetheless be normalized to condition document representations. We propose to compare the original LDA vector representation (without normalization) with two normalization approaches, the Eigen Factor Radial (EFR) and the Feature Warping (FW) methods, already successfully applied in speaker recognition field, but never compared and evaluated in the context of a speech analytic task. Results show the interest of these normalization techniques for theme identification tasks using automatic transcriptions The EFR normalization approach allows a gain of 3.67 and 3.06 points respectively in comparison to the absence of normalization and to the FW normalization technique.
Fichier principal
Vignette du fichier
a95fb85e4082ca795c374857f347d090a851.pdf (716.48 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-02356373 , version 1 (14-11-2019)

Identifiers

  • HAL Id : hal-02356373 , version 1

Cite

Mohamed Morchid, Richard Dufour, Driss Matrouf. A Comparison of Normalization Techniques Applied to Latent Space Representations for Speech Analytics. Interspeech 2015, Sep 2015, Dresden, Germany. ⟨hal-02356373⟩

Collections

UNIV-AVIGNON LIA
29 View
36 Download

Share

Gmail Facebook X LinkedIn More