Abstract: A speech corpus creation method and system are disclosed. The method comprising identifying a publicly accessible first source of the first speech data and its corresponding first text transcription; extracting a second speech data of an accessible encoding format from the first speech data; extracting a second text transcription data with at least one encoding format from the first text transcription data; matching and aligning the transcription to the extracted second speech data at a sentence, word, phoneme level, or combination thereof to form a first and a second speech corpus; analyzing the text transcriptions in the second speech corpus to identify the short speech segments to produce a phonetically balanced, segmented, text aligned third speech corpus; and conditioning the third speech corpus by inserting a context and associated environment richer corpus therein the third speech corpus from at least one second source to form the final speech corpus.

Abstract: The present disclosure relates generally to interactive response systems, and more particularly to systems and methods for providing multi-modality interaction between communication devices. In one embodiment, a multi-modality interactive system is disclosed, comprising: a processor; and a memory storing processor-executable instructions comprising instructions to: obtain a request to initiate an interactive session with a communication device; obtain interactive session data for communication to the communication device; select a modality for the interactive session data, by analyzing one or more parameters associated with the interactive session data and the communication device; convert a format of the interactive session data according to the selected modality; and transmit the interactive session data in the converted format to the communication device.

Abstract: A system and method for porting of existing speech recognition solutions in a source language to a target language has been disclosed. The system envisaged by the present invention enables porting of a working speech recognition solution in the source language to a working system in the target language, thus minimizing the development process and reusing existing speech recognition solution components to recognize multiple languages.

Abstract: The present invention provides a frugal method for extraction of speech data and associated transcription from plurality of web resources (internet) for speech corpus creation characterized by an automation of the speech corpus creation and cost reduction. An integration of existing speech corpus with extracted speech data and its transcription from the web resources to build an aggregated rich speech corpus that are effective and easy to adapt for generating acoustic and language models for (Automatic Speech Recognition) ASR systems.

Abstract: The present invention proposes a system and a method to enable an IVR mashup interface to ease the selection of services over a communication device and enhances the caller experience by ways of personalizing the call and making effective use of the call hold time. The said system and method as implemented by the mashup server automatically connects the caller to the most immediate service offering service provider after simultaneously placing of the call to various service providers. In the mean time, the mashup server simultaneously calculates the wait time to get connected to service provider after a call is made to mashup service and relays appropriate promotional content to the caller based on such wait time and the profile of the user. Further the system and method as proposed is capable of representing a user and transact on behalf of the user by talking to the live agents or interacting with the automated IVR systems representing the service providers.

Abstract: A system and method of multi-objective visualization utilize a multiple-objective optimizer approach to multi-objective optimization and specifically utilize a method for exploring and visualizing Pareto surfaces for any number of dimensions using an interactive graphical user interface. The general solution is to maintain all natural problem objectives separately and use a special multiple-objective optimizer to solve the problem. In this case there is no single solution point. Rather, the solution is a hyper dimensional surface in an objective space with various surface points representing different tradeoffs between objectives.

Abstract: A system and method for porting of existing speech recognition solutions in a source language to a target language has been disclosed. The system envisaged by the present invention enables porting of a working speech recognition solution in the source language to a working system in the target language, thus minimising the development process and reusing existing speech recognition solution components to recognise multiple languages.

Abstract: The invention relates to a system and method for detecting a closing of a solenoid. The system includes a capacitive charge circuit electrically coupled to the solenoid. The capacitive charge circuit conditions the current flow through the solenoid to increase the current in response to the closing of the solenoid. The invention also relates to a system and method that includes detecting a current through the solenoid and determining a current slope characteristic. The current slope characteristic is a function of the current and time. The method also includes conditioning an electrical characteristic of the solenoid such that the conditioning is in response to a current slope parameter. The current slope parameter defines a change in the current after removal of an electrical charge to the solenoid.

Abstract: Disclosed herein are methods of generating a virtual crankshaft positioning stream of signal pulses that is derived from one or more series of actual crank signals. The virtual stream is useful for monitoring crankshaft positioning and is able to persist despite electromagnetic disturbances in the series of actual crank signals.

Abstract: Disclosed herein are methods of cranking and/or operating an engine that eliminates the need for use of a cam sensor. The methods implemented with internal combustion engine comprising a plurality of cylinders whose firing sequence occurs over two revolutions of a crankshaft with a first set of cylinders comprising a power stroke during the first crankshaft revolution and a second set of cylinders comprising the power stroke of a second crankshaft revolution. The methods involve manipulating fuel injection command signals to occur out of their proper sequence, monitoring and engine indicator responsive to firing and non-firing of cylinders, and identifying correct engine phase based on fluctuations in the engine indicator. Also disclosed herein are software product embodiments comprising program code modules that cause a engine control unit to manipulate the generation of fuel injection command signals to take place outside their correct sequence.

Abstract: A system (400) and method of determining fuel demands of a locomotive engine (10) based upon engine speed and power produced by the engine at a given time, so to optimize the engine's power output for a load while reducing engine emissions. The engine control architecture comprises three interrelated control loops (100–300). A primary feedback control loop (100) employs integral type control with gain scheduling to regulate engine speed to commanded slew rated based upon the locomotive's operator commands. A second control loop (200) provides an active, feed forward or predictive control consisting of a plurality of correction functions each utilizing a Taylor series having coefficients for each term in the series, the coefficients being modified to adapt the system to the engine with which it is used.

Abstract: Disclosed herein are methods of cranking and/or operating an engine that eliminates the need for use of a cam sensor. The methods implemented with internal combustion engine comprising a plurality of cylinders whose firing sequence occurs over two revolutions of a crankshaft with a first set of cylinders comprising a power stroke during the first crankshaft revolution and a second set of cylinders comprising the power stroke of a second crankshaft revolution. The methods involve manipulating fuel injection command signals to occur out of their proper sequence, monitoring and engine indicator responsive to firing and non-firing of cylinders, and identifying correct engine phase based on fluctuations in the engine indicator. Also disclosed herein are software product embodiments comprising program code modules that cause a engine control unit to manipulate the generation of fuel injection command signals to take place outside their correct sequence.

Abstract: Disclosed herein are methods of generating an active crank series of signals that is derived from at least two series of signals, wherein one or both of the series of signals have been modulated to produce two series of signals that resemble each other. Also disclosed herein is a crankshaft positioning system for determining the rotational position of a crankshaft of an engine that utilizes at least two crank angle sensors 10 and 12. The signal information from the two crank angle sensors 10 and 12 is processed by a signal processor 150 such that the series of signals 220 from the second crank angle sensor 12 emulates the series of signals 210 from the first crank angle processor 10. The signal processor generates an active crank series of signals 230 based on the two series of signals 210, 220. The active crank series of signals 230 is sent to an engine control processor 120 which directs the injection and/or ignition of fuel into cylinders of an engine.

Abstract: A system (400) and method of determining fuel demands of a locomotive engine (10) based upon engine speed and power produced by the engine at a given time, so to optimize the engine's power output for a load while reducing engine emissions. The engine control architecture comprises three interrelated control loops (100-300). A primary feedback control loop (100) employs integral type control with gain scheduling to regulate engine speed to commanded slew rated based upon the locomotive's operator commands. A second control loop (200) provides an active, feed forward or predictive control consisting of a plurality of correction functions each utilizing a Taylor series having coefficients for each term in the series, the coefficients being modified to adapt the system to the engine with which it is used.

Abstract: The invention relates to a system and method for detecting a closing of a solenoid. The system includes a capacity charge circuit electrically coupled to the solenoid. The capacity charge circuit conditions the current flow through the solenoid to increase the current in response to the closing of the solenoid. The invention also relates to a system and method that includes detecting a current through the solenoid and determining a current slope characteristic. The current slope characteristic is a function of the current and time. The method also includes conditioning an electrical characteristic of the solenoid such that the conditioning is in response to a current slope parameter. The current slope parameter defines a change in the current after removal of an electrical charge to the solenoid.