摘要:
Methods, systems, and products for testing a grammar used in speech recognition for reliability in a plurality of operating environments having different background noise that include: receiving recorded background noise for each of the plurality of operating environments; generating a test speech utterance for recognition by a speech recognition engine using a grammar; mixing the test speech utterance with each recorded background noise, resulting in a plurality of mixed test speech utterances, each mixed test speech utterance having different background noise; performing, for each of the mixed test speech utterances, speech recognition using the grammar and the mixed test speech utterance, resulting in speech recognition results for each of the mixed test speech utterances; and evaluating, for each recorded background noise, speech recognition reliability of the grammar in dependence upon the speech recognition results for the mixed test speech utterance having that recorded background noise.
摘要:
A method and system for automated code generation in a call flow builder (10) can include a display coupled to a processor. The processor can be programmed to select a real code (database connection) or a prototype code using a graphical interface (20) to provide a selected code and develop a call flow using the selected code. The processor can be programmed to select the prototype code as the selected code, test the call flow in a local development environment and further enable the switching of the selected code from the prototype to the real code to complete a database connection. The processor can be further programmed to enable specification of a default or range of values. Additionally, the processor can be programmed to use a database connection code that replaces a prototype assignment of values to variables when the real code is the selected code.
摘要:
A method (100) and system (30) to enable automatic generation and testing of voice applications includes generating (102) a test driver application (TDA) (32) and generating (104) a modified original voice application (34) to be tested by the TDA within a call flow builder (10). The modified application can include or generate (106) “test hooks” or more particularly DTMF tones and DTMF grammars that can be used to synchronize the modified original voice application with the TDA. The TDA can test (110) all possible paths of the modified original voice application. Note the TDA and the modified original voice application can be generated and/or tested (112) in a test environment within the call flow builder or a telephony environment. The TDA can be automatically generated (108) to exercise all possible flows where the DTMF tones define the current state and location of the modified application.
摘要:
Methods, systems, and products for testing a grammar used in speech recognition for reliability in a plurality of operating environments having different background noise that include: receiving recorded background noise for each of the plurality of operating environments; generating a test speech utterance for recognition by a speech recognition engine using a grammar; mixing the test speech utterance with each recorded background noise, resulting in a plurality of mixed test speech utterances, each mixed test speech utterance having different background noise; performing, for each of the mixed test speech utterances, speech recognition using the grammar and the mixed test speech utterance, resulting in speech recognition results for each of the mixed test speech utterances; and evaluating, for each recorded background noise, speech recognition reliability of the grammar in dependence upon the speech recognition results for the mixed test speech utterance having that recorded background noise.
摘要:
Methods, apparatus, and products are disclosed for adjusting a speech engine for a mobile computing device based on background noise, the mobile computing device operatively coupled to a microphone, that include: sampling, through the microphone, background noise for a plurality of operating environments in which the mobile computing device operates; generating, for each operating environment, a noise model in dependence upon the sampled background noise for that operating environment; and configuring the speech engine for the mobile computing device with the noise model for the operating environment in which the mobile computing device currently operates.
摘要:
A list presentation method. The list presentation method can include the steps of: dynamically grouping selected items in a list based on sequentially positioned symbols in the items which are common to one another; labeling each group of selected items; audibly presenting each group label through a speech user interface; and, responsive to a selection of one of the presented group labels, presenting through the speech user interface items in a group corresponding to the selected group label.
摘要:
A method for constructing speech elements within an interface can include a step of identifying a visual interface having multiple visual elements. Visual selectors can be presented proximate each of the visual elements. The visual selectors can permit a user to input a speech control type for the associated visual element. For each presented visual selector, a speech element having a speech control type specified in the visual selector can be automatically generated.
摘要:
Embodiments in accordance with the invention can include a new method (500) and system (100) for testing code within a speech application. A test file (101) can be automatically generated to verify the functionality of a new section of code (172) presented within a graphical call flow builder application (156). In one arrangement, a user can specify through a wizard two points on a path identifying the code section to be tested. The wizard can generate a test file (101) and can configure a path (151) to a new subpath (152) and automatically assign predetermined values to graphical call flow prompts along the path. In this manner, the new code section is reached under the same path conditions for allowing repeatable testing. The system can include a test harness (110) configured to test a new code section from within a context of the speech application, and a test controller (120) for transitioning to the new code section. The test controller can run the test harness within the speech application to evaluate a functionality of the new code section.
摘要:
The present invention addresses problems associated with accessing and using automated systems for scheduled travel events and provides a method and system for communicating information to a user interacting with an automated system for accessing travel schedule data. In a first embodiment of the present invention, a user request can be processed for an event scheduled on an automated system. An occurrence time for the scheduled event can then be loaded. If the occurrence time is within a preconfigured time interval including midnight, a disambiguation process can be triggered for the scheduled event. The scheduled event can be an airline flight and the occurrence time can be an arrival or departure time. The disambiguation process can include prompting a user with a disambiguation message, wherein the disambiguation message makes reference to either an arrival date for the airline flight or a departure date for the airline flight.
摘要:
A method (10) in a speech recognition application callflow can include the steps of assigning (11) an individual option and a pre-built grammar to a same prompt, treating (15) the individual option as a valid output of the pre-built grammar if the individual option is a potential valid match to a recognition phrase (12) or an annotation (13) in the pre-built grammar, and treating (14) the individual option as an independent grammar from the pre-built grammar if the individual option fails to be a potential valid match to the recognition phrase or the annotation in the pre-built grammar.