18 526 834 livres à l’intérieur 175 langues
2 956 572 livres numériques à l’intérieur 111 langues
Cela ne vous convient pas ? Aucun souci à se faire ! Vous pouvez retourner les articles jusqu'à 30 jours
Impossible de faire fausse route avec un bon d’achat. Le destinataire du cadeau peut choisir ce qu'il veut parmi notre sélection.
Jusqu'à 30 jours pour les retours
Automated speech recognition, historically posed as asolvable problem, has thus far eluded algorithmic solutions andcontinues to be outperformed by humans. Conventional speechrecognizers employ a training phase during which many of theirparameters are configured. During normal operation, theserecognizers do not significantly alter these parameters. Converselythe model proposed in this book draws heavily on high level humanthought patterns and speech perception to outline a set of preceptsto eliminate this training phase and instead opt to perform all itstasks during normal operation. Background on the problems in thisfield and their classical solutions are presented followed bymotivation and implementation details of the proposed model. Thetesting results of this model indicate that benefits can be seen inincreased speech recognizer adaptability while still retainingcompetitive recognition rates in controlled environments. This bookis intended for researchers in artificial intelligence and speechrecognition. It is also suitable for for those attempting to learnthe subject area.
Bonjour ! Je suis Libroamiko, votre conseiller littéraire.
Comment puis-je vous aider ?