Compact Acoustic Models for Embedded Speech Recognition - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue EURASIP Journal on Audio, Speech, and Music Processing Année : 2009

Compact Acoustic Models for Embedded Speech Recognition

Résumé

Recommended by Joe Picone Speech recognition applications are known to require a significant amount of resources. However, embedded speech recognition only authorizes few KB of memory, few MIPS, and small amount of training data. In order to fit the resource constraints of embedded applications, an approach based on a semicontinuous HMM system using state-independent acoustic modelling is proposed. A transformation is computed and applied to the global model in order to obtain each HMM state-dependent probability density functions, authorizing to store only the transformation parameters. This approach is evaluated on two tasks: digit and voice-command recognition. A fast adaptation technique of acoustic models is also proposed. In order to significantly reduce computational costs, the adaptation is performed only on the global model (using related speaker recognition adaptation techniques) with no need for state-dependent data. The whole approach results in a relative gain of more than 20% compared to a basic HMM-based system fitting the constraints.

Dates et versions

hal-01318188 , version 1 (19-05-2016)

Identifiants

Citer

Christophe Lévy, Georges Linarès, Jean-François Bonastre. Compact Acoustic Models for Embedded Speech Recognition. EURASIP Journal on Audio, Speech, and Music Processing, 2009, ⟨10.1155/2009/806186⟩. ⟨hal-01318188⟩

Collections

UNIV-AVIGNON LIA
33 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More