Abstract: A method and system for interacting with a speech recognition system. A lattice of candidate words is displayed. The lattice of candidate words may include the output of a speech recognizer. Candidate words representing temporally serial utterances may be directly joined in the lattice. A path through the lattice represents a selection of one or more candidate words interpreting one or more corresponding utterances. An interface allows a user to select a path in the lattice. A selection of the path in the lattice may be received and the selection may be stored. The selection may be provided as positive feedback to the speech recognizer.

Abstract: A computer-implemented method is disclosed for creating a grammar to be processed by a speech recognition engine in the context of a voice-activated command system. The method includes receiving a database containing a plurality of terms and identifying a set of terms that are pronounced the same but spelled differently. The method also includes placing a single term within the grammar to represent the set of terms.

Abstract: Speech log data is received, and possible semantic classifications for that log data are obtained from grammars that were active in the system when the log data was received. Audio information from the log data, along with the possible semantic values, are then presented for user selection. A user selection is received, and corrected log data is generated based on the user selected semantic value.

Abstract: A method is disclosed from constructing a grammar. The grammar is configured to be processed by a speech recognition engine in the context of a voice-activated command system. The method includes receiving a database containing a plurality of terms. From the plurality of terms, first and second terms are identified. The first and second terms are spelled differently but have a first pronunciation in common. One of the first and second terms also has a second pronunciation that is not inherent to the other of the first and second terms. The first and second pronunciations are placed within the grammar.

Abstract: A speech recognition system for secure information. Embodiments of the speech recognition system include a sub-word speech recognition component, which interfaces with a security system. The sub-word speech recognition component provides sub-word speech units for an input utterance, such as a password or security code. The sub-word speech units for the input utterance are provided to the security system for authentication.

Abstract: A speech grammar is generated using possible answer forms to input prompts. In one embodiment, input prompts are provided to a response prediction system which generates predicted responses to the input prompts. A grammar is pre-populated with the predicted responses.

Abstract: A follow-up call to a user is made after completion of a first call with a voice user interface module operable on a computer. The voice user interface module inquiries about information communicated in the first call.

Abstract: A method of generating an optimized grammar, for use in speech recognition, from a data set or big list of items, is disclosed. The method includes the steps of obtaining a tree representing items in the data set, and generating the grammar using the tree. The tree or tree data structure representing items in the data set is a simulated recognition search tree, representing items in the data set, which can be automatically generated from the data set.

Abstract: A method of allowing a user to provide constrained, mixed-initiative utterances in order to improve accuracy and avoid disambiguation dialogs when recognition of a user's audible input would otherwise render a number of possible selections from the database or list is provided. A grammar is adapted to include additional information associated with at least some of the entries. The additional information forms part of the information conveyed by the use in the constrained, mixed-initiative utterance.

Abstract: A method of facilitating interaction between a user and an automated system is provided. The method includes generating a graphical user interface on a display, with the graphical user interface inviting the user to provide an input to initiate execution of an operation. Upon receipt of an input from the user, a telephone call is automatically generated or initiated from the automated system to the user. The automated system can then prompt the user as required to execute the operation.

Abstract: A method of providing information to a user in a telephone interactive system includes receiving a new call. A comparison is then made between an identifier associated with the new call with stored call information pertaining to previous calls. If the identifier associated with the new call matches an identifier associated with a previous call, a subsequent action taken in the new call is based on context information stored from the previous call.

Abstract: A method of executing operations in a voice-activated command system includes automatically initiating execution of a default operation. A user is then prompted, after the default operation has been initiated, to determine whether the user wishes to execute a second operation instead of the default operation. If the user wishes to execute the second operation instead of the default operation, execution of the default operation is terminated and execution of the second operation is initiated. In voice-activated and other command systems, such as voice dialing systems, this method allows the command system to execute the most probable operation without delay, while still making the system easily navigable by naïve users. Systems, computer readable medium and apparatus which implement the methods of the present invention are also disclosed.

Abstract: A method of providing voice dialing assistance includes providing a first input to a speech recognition engine, with the first input corresponding to a speech sample provided by a caller attempting to reach an intended call recipient. A speech recognition output is generated in response to the first input. A potential call recipient is identified based upon the speech recognition output. A confirmation that the potential call recipient is the intended call recipient is implemented using a personal recording made by the potential call recipient.

Abstract: A method of querying a user to select from a list in a voice-activated command system is provided. The method includes generating command prompt phrases during which the user can select items on the list. The command prompt phrases include an item on the list and an index for another item on the list. In some embodiments, each command prompt phrase also includes a period of silence between item on the list and the index for another item on the list. If a user selecting barge-in is received during a particular command prompt phrase, the corresponding item on the list is selected.

Abstract: A speech recognition application including a recognition module configured to receive input utterances and an application module configured to select a recognition from the speech recognition module using output from a first iteration to select a recognition result for a second iteration. In one embodiment, the application module eliminates a previous rejected recognition result or results from the N-Best list for recognition. In another embodiment, the application module rescores N-Best entries based upon N-Best lists or information from another iteration. In another illustrated embodiment, the application module uses a limited grammar from a current N-Best list for subsequent recognition, for example for rerecognition using a recorded input from a previous iteration.

Abstract: A method is disclosed from constructing a grammar. The grammar is configured to be processed by a speech recognition engine in the context of a voice-activated command system. The method includes receiving a database containing a plurality of terms. From the plurality of terms, first and second terms are identified. The first and second terms are spelled differently but have a first pronunciation in common. One of the first and second terms also has a second pronunciation that is not inherent to the other of the first and second terms. The first and second pronunciations are placed within the grammar.

Abstract: A computer-implemented method is disclosed for creating a grammar to be processed by a speech recognition engine in the context of a voice-activated command system. The method includes receiving a database containing a plurality of terms and identifying a set of terms that are pronounced the same but spelled differently. The method also includes placing a single term within the grammar to represent the set of terms.

Abstract: A process for collecting the identity of a telephone caller is disclosed. In one embodiment, a personalized Context Free Grammar (CFG) is created for each potential call recipient, and is configured to support identification of incoming callers utilizing voice recognition. Each CFG incorporates an indication of high probability callers and probability weights in each CFG are altered accordingly. When a recipient receives a call, the relevant CFG is applied in association with a voice recognition application to enable at least a preliminary identification of the caller. In accordance with another embodiment, the caller confirms identifications. In accordance with one embodiment, standard caller-ID functionality is utilized if possible at least to assist in the caller identification process. In accordance with still another embodiment, voice recognition enhanced caller identification is utilized to provide intelligent call routing functionality.