Abstract: A method, computer program and system for generating code of the vocal interface of a software application by reading the persistent data of an application designed by a data meta model using a design language such as UML (Unified Modeling Language) defining a hierarchical organization of classes, their attributes and the relations between classes. Similarly to the wizard for graphical user interface the vocal interface code comprises dialog unit code, which is Forms when VoiceXML language is used, to allow at execution time, entry of data for the application in a guided way.

Abstract: The present invention proposes a method, system and computer program for speech recognition. According to one embodiment, a method is provided wherein, for an expected input string divided into a plurality of expected string segments, a speech segment is received for each expected string segment. Speech recognition is then performed separately on each said speech segment via the generation, for each said speech segment, of a segment n-best list comprising n highest confidence score results. A global n-best list is then generated corresponding to the expected input string utilizing the segment n-best lists and a final global speech recognition result corresponding to said expected input string is determined via the pruning of the results of the global n-best list utilizing a pruning criterion.

Abstract: A method, computer program and system for generating code of the vocal interface of a software application by reading the persistent data of an application designed by a data meta model using a design language such as UML (Unified Modeling Language) defining a hierarchical organization of classes, their attributes and the relations between classes. Similarly to the wizard for graphical user interface the vocal interface code comprises dialog unit code, which is Forms when VoiceXML language is used, to allow at execution time, entry of data for the application in a guided way.

Abstract: The present invention proposes a method, system and computer program for speech recognition. According to one embodiment, a method is provided wherein, for an expected input string divided into a plurality of expected string segments, a speech segment is received for each expected string segment. Speech recognition is then performed separately on each said speech segment via the generation, for each said speech segment, of a segment n-best list comprising n highest confidence score results. A global n-best list is then generated corresponding to the expected input string utilizing the segment n-best lists and a final global speech recognition result corresponding to said expected input string is determined via the pruning of the results of the global n-best list utilizing a pruning criterion.