Characterizing Feature Variability in Automatic Speech Recognition Systems

Loïc Barrault (1, 2) , Driss Matrouf (2) , Renato de Mori (2) , Roberto Gemello (3) , Franco Mana (3)

1 LIUM - Laboratoire d'Informatique de l'Université du Maine
2 LIA - Laboratoire Informatique d'Avignon
3 LOQUENDO - LOQUENDO

A method is described for predicting acoustic feature variability by analyzing the consensus and relative entropy of phoneme posterior probability distributions obtained with different acoustic models having the same type of observations. Variability prediction is used for diagnosis of automatic speech recognition (ASR) systems. When errors are likely to occur, different feature sets are considered for correcting recognition results. Experimental results are provided on the CH1 Italian portion of AURORA3.

Mots clés: feature variability; asr system diagnosis

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Loïc Barrault, Driss Matrouf, Renato de Mori, Roberto Gemello, Franco Mana. Characterizing Feature Variability in Automatic Speech Recognition Systems. International Conference on Acoustics, Speech and Language Processing, May 2006, Toulouse, France. pp.1029-1032. ⟨hal-00433095⟩