A method and apparatus accesses a database where entries are linked to at least two sets of patterns. One or more patterns of a first set of patterns are recognized within a received signal. The recognized patterns are used to identify entries and compile a list of patterns in a second set of patterns to which those entries are also linked. The list is then used to recognize a second received signal. The received signals may, for example, be voice signals or signals indicating the origin or destination of the received signals.
A method for controlling an information system during the output of stored information segments via a signaling device (50a). Useful information is stored in a database (32) for being requested, from which information at least one information segment is specified as a first data segment (W1) via a first voice signal (s.sub.a(t),s.sub.a(z)) and is provided via a control output (20,40,50;50a) or is converted (50b) into a control signal for a technical device (G). The information is organized in the database such that an initially limited first information area (32a) of stored information is accessible (4,4a,4b) to said voice signal, for selecting the specified information segment therefrom. A further information area (32b,32c,32d) of said database (32) is activated (59,70,4c,4d) as a second information area, if the information segment (W1) corresponding to a first voice signal segment (s1) of said first voice signal (s.sub.a(t) is not contained in said first information area (32a). When accessing information of the database, a robust word recognition is obtained and the request is successfully processed within a short time.
The invention concerns method and system for pre-processing entries in a directory listings. An automated attendant or automated directory listings assistant may use the pre-processed entries. A first directory listings including one or more fields may be received. The one or more fields may be populated with entries including one or more symbol strings. A second directory listings including one or more fields may be received. The one or more fields of the second directory listings may be populated with entries including one or symbol strings. Entries in the one or more fields of the first directory listings may be correlated with entries in the corresponding one or more fields of the second directory listings. Entries, in the one or more fields of the first directory listings, which do not correlate with entries in the corresponding one or more fields of the second directory listings may be identified. The identified entries may be processed using a rule set corresponding to the field in which the entry is located. Based on the rule set, a corresponding confidence level for the processed entries may be determined. The processed entries having the corresponding confidence level meeting or exceeding a threshold may be automatically modified. The automatically modified entries may be outputted for processing. In alternative embodiments of the present invention, the processed entries having the corresponding confidence level below the threshold may be marked for operator confirmation.
A method and apparatus for creating modifiable and combinable Speech Objects for use in an interactive voice response (IVR) environment. Each Speech Object is for acquiring a particular type of information from a speaker during an interaction between the speaker and a speech recognition mechanism. A Speech Object is an instantiation of a user-extensible class that includes properties, such as prompts and grammars, associated with the corresponding type of interaction. A Speech Object further includes logic for controlling the interaction with the user when executed in a processing system. A Speech Object can be subclassed to add additional properties and functionality to create customized Speech Objects, or such properties can be altered at runtime. Multiple Speech Objects, each for acquiring a particular type of information, can be combined to form a compound Speech Object.
This invention relates to a method of recognizing a speech utterance (s) available in spelled form, comprising a processing stage in which a corresponding letter sequence (r) is estimated by means of a letter speech recognition unit (2) based on Hidden Markov Models, and a second processing stage (3) in which the estimated result (r) produced by the first processing stage utilizing a statistical letter sequence model (4) and a statistical model (5) for the speech recognition unit (2) is post-processed, while the dynamic programming method is used during the post-processing. For providing robust and efficient speech recognition procedures for the use of speech signals for system control, a grid structure on which the dynamic programming is based and whose node points are provided for the assignment to accumulated probability values, is converted into a tree structure and that an A* algorithm is used for finding an optimum tree path. Also a speech control device wherein a complete word is input as a control signal and at least part of this word in spelled form is input, while the result of the letter speech recognition is used within the scope of the word speech recognition.
Disclosed are an interactive system and method of controlling the same for achieving a task more efficiently. Items of data to be searched are stored in a memory (107) in a form classified according to prescribed classes, and a dialog controller (102) decides the order in which questions are presented to a user in order to narrow down the object of a search to data in a specific class. The questions are then presented to the user in the decided order by a question generator (103).
