Analyzing Learned Representations of a Deep ASR Performance Prediction Model - CIMEOS Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Analyzing Learned Representations of a Deep ASR Performance Prediction Model

Résumé

This paper addresses a relatively new task: prediction of ASR performance on unseen broadcast programs. In a previous paper, we presented an ASR performance prediction system using CNNs that encode both text (ASR transcript) and speech, in order to predict word error rate. This work is dedicated to the analysis of speech signal embeddings and text em-beddings learnt by the CNN while training our prediction model. We try to better understand which information is captured by the deep model and its relation with different conditioning factors. It is shown that hidden layers convey a clear signal about speech style, accent and broadcast type. We then try to leverage these 3 types of information at training time through multi-task learning. Our experiments show that this allows to train slightly more efficient ASR performance prediction systems that-in addition-simultaneously tag the analyzed utterances according to their speech style, accent and broadcast program origin.
Fichier principal
Vignette du fichier
emnlp2018.pdf (626.71 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01863293 , version 1 (28-08-2018)

Identifiants

  • HAL Id : hal-01863293 , version 1

Citer

Zied Elloumi, Laurent Besacier, Olivier Galibert, Benjamin Lecouteux. Analyzing Learned Representations of a Deep ASR Performance Prediction Model. Blackbox NLP Workshop and EMLP 2018, Nov 2018, Bruxelles, Belgium. ⟨hal-01863293⟩
68 Consultations
82 Téléchargements

Partager

Gmail Facebook X LinkedIn More