Pattern processing system specific to a user group

Abstract

Methods and apparatus for identifying a user group in connection with user group-based speech recognition. An exemplary method comprises receiving, from a user, a user group identifier that identifies a user group to which the user was previously assigned based on training data. The user group comprises a plurality of individuals including the user. The method further comprises using the user group identifier, identifying a pattern processing data set corresponding to the user group, and receiving speech input from the user to be recognized using the pattern processing data set.

1 . A method of pattern processing, in particular for speech processing, comprising the steps of: 
 receiving ( 104 ) a unique identifier of a user group laid down for the user, and    using ( 105 ) a pattern processing data set ( 80  . . .  81 ) specific to said user group for the processing ( 110 ) of a pattern input of the user.    
     
     
         2 . A method as claimed in  claim 1 , characterized in that the definition of the user group for the user takes place in a training phase.  
     
     
         3 . A method as claimed in  claim 1  or  2 , characterized in that the definition of the user group for the user can be influenced by the user.  
     
     
         4 . A method as claimed in any one of the  claims 1  to  3 , characterized in that user inputs are made into a public user terminal ( 10 ), in particular a bank terminal, an automatic ticket vending machine, or an information kiosk.  
     
     
         5 . A method as claimed in any one of the  claims 1  to  4 , characterized in that user inputs are provided via a network ( 20 ), in particular the Internet.  
     
     
         6 . A method as claimed in any one of the  claims 1  to  5 , characterized in that the following items form part of a pattern processing data set ( 80  . . .  81 ) for speech recognition specific to a user group: 
 a language and/or dialect specific to the user group,  
 a feature extraction specific to the user group, in particular a normalization of vocal-tract length specific to the user group,  
 an acoustic reference model specific to the user group,  
 a vocabulary specific to the user group,  
 a language model specific to the user group, and/or  
 a dialogue model specific to the user group.  
 
     
     
         7 . The use of a method as claimed in any one of the  claims 1  to  6  for obtaining information and/or for giving orders, in particular for carrying out bank transactions.  
     
     
         8 . A pattern processing system, in particular a speech processing system, which is designed for 
 receiving ( 104 ) a unique identifier of a user group laid down for the user, and    using ( 105 ) a pattern processing data set ( 80  . . .  81 ) specific to said user group for processing ( 110 ) a pattern input of the user.