Speech recognition is being addressed as one of the key technologies for a natural interaction with robots, that are targeting in the consumer market. However, speech recognition in human-robot interaction is typically affected by noisy conditions of the operational environment, that impact on the performance of the recognition of spoken commands. Consequently, finite-state grammars or statistical language models even though they can be tailored to the target domain exhibit high rate of false positives or low accuracy. In this paper, a discriminative re-ranking method is applied to a simple speech and language processing cascade, based on off-the-shelf components in realistic conditions. Tree kernels are here applied to improve the accuracy of the recognition process by re-ranking the nbest list returned by the speech recognition component. The rationale behind our approach is to reduce the effort for devising domain dependent solutions in the design of speech interfaces for language processing in human-robot interactions. © Springer International Publishing Switzerland 2013.
Kernel-based discriminative re-ranking for spoken command understanding in HRI / Roberto, Basili; Bastianelli, Emanuele; Giuseppe, Castellucci; Nardi, Daniele; Vittorio, Perera. - 8249 LNAI:(2013), pp. 169-180. (Intervento presentato al convegno 13th International Conference of the Italian Association for Artificial Intelligence, AI*IA 2013 tenutosi a Turin nel 4 December 2013 through 6 December 2013) [10.1007/978-3-319-03524-6_15].
Kernel-based discriminative re-ranking for spoken command understanding in HRI
BASTIANELLI, EMANUELE;NARDI, Daniele;
2013
Abstract
Speech recognition is being addressed as one of the key technologies for a natural interaction with robots, that are targeting in the consumer market. However, speech recognition in human-robot interaction is typically affected by noisy conditions of the operational environment, that impact on the performance of the recognition of spoken commands. Consequently, finite-state grammars or statistical language models even though they can be tailored to the target domain exhibit high rate of false positives or low accuracy. In this paper, a discriminative re-ranking method is applied to a simple speech and language processing cascade, based on off-the-shelf components in realistic conditions. Tree kernels are here applied to improve the accuracy of the recognition process by re-ranking the nbest list returned by the speech recognition component. The rationale behind our approach is to reduce the effort for devising domain dependent solutions in the design of speech interfaces for language processing in human-robot interactions. © Springer International Publishing Switzerland 2013.File | Dimensione | Formato | |
---|---|---|---|
VE_2013_11573-670013.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
343.84 kB
Formato
Adobe PDF
|
343.84 kB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.