The present invention provides a pronunciation error detection apparatus capable of following a text without the need for a correct sentence even when erroneous recognition such as a reading error occurs. The pronunciation error detection apparatus comprises: a speech recognition part that recognizes the speech in speech data based on a speech recognition model for a non-native speaker, and outputs speech recognition results, reliability and time information; a reliability determination part that outputs the speech recognition results with higher reliability than a predetermined threshold and the corresponding time information as the determined speech recognition results and the determined time information; and a pronunciation error detection part that outputs a phoneme as a pronunciation error when reliability for each phoneme in the speech recognition results using the native speaker speech recognition model under a weakly constraining grammar is greater than the reliability of the corresponding phoneme in the speech recognition results using the native speaker acoustic model under a constraining grammar in which the determined speech recognition results are correct for the speech data in a segment specified by the determined time information.

The present invention provides a pronunciation error detection apparatus capable of following a text without the need for a correct sentence even when erroneous recognition such as a reading error occurs. The pronunciation error detection apparatus comprises: a speech recognition part that recognizes the speech in speech data based on a speech recognition model for a non-native speaker, and outputs speech recognition results, reliability and time information; a reliability determination part that outputs the speech recognition results with higher reliability than a predetermined threshold and the corresponding time information as the determined speech recognition results and the determined time information; and a pronunciation error detection part that outputs a phoneme as a pronunciation error when reliability for each phoneme in the speech recognition results using the native speaker speech recognition model under a weakly constraining grammar is greater than the reliability of the corresponding phoneme in the speech recognition results using the native speaker acoustic model under a constraining grammar in which the determined speech recognition results are correct for the speech data in a segment specified by the determined time information.

A method is implemented by a computing device for helping a particular user use a user interface (UI). Electroencephalography (EEG) data is obtained that indicates brain activity of a particular user during a period in which that user views the UI and/or interprets help information that describes how to use the UI. Based on the EEG data, the computing device selects, from among multiple predefined cognitive states, the one or more cognitive states that characterize the particular user during the period. The computing device assists the particular user to use the UI by customizing the help information for the particular user based on the one or more selected cognitive states. A complementary computing device and computer program product are also disclosed.

A method is implemented by a computing device for helping a particular user use a user interface (UI). Electroencephalography (EEG) data is obtained that indicates brain activity of a particular user during a period in which that user views the UI and/or interprets help information that describes how to use the UI. Based on the EEG data, the computing device selects, from among multiple predefined cognitive states, the one or more cognitive states that characterize the particular user during the period. The computing device assists the particular user to use the UI by customizing the help information for the particular user based on the one or more selected cognitive states. A complementary computing device and computer program product are also disclosed.

A real-time virtual reality welding system including a programmable processor-based subsystem, a spatial tracker operatively connected to the programmable processor-based subsystem, at least one mock welding tool capable of being spatially tracked by the spatial tracker, and at least one display device operatively connected to the programmable processor-based subsystem. The system is capable of simulating, in virtual reality space, a weld puddle having real-time molten metal fluidity and heat dissipation characteristics. The system is further capable of importing data into the virtual reality welding system and analyzing the data to characterize a student welder's progress and to provide training.

A real-time virtual reality welding system including a programmable processor-based subsystem, a spatial tracker operatively connected to the programmable processor-based subsystem, at least one mock welding tool capable of being spatially tracked by the spatial tracker, and at least one display device operatively connected to the programmable processor-based subsystem. The system is capable of simulating, in virtual reality space, a weld puddle having real-time molten metal fluidity and heat dissipation characteristics. The system is further capable of importing data into the virtual reality welding system and analyzing the data to characterize a student welder's progress and to provide training.

A method of treatment for intellectual and developmental disabilities is disclosed herein, wherein the method includes the steps of diagnosing an intellectual or developmental disability in an individual, matching symptoms or characteristics associated with the individual's intellectual or developmental disability, researching what personality traits, interpersonal skills, or life skills are affected by the symptoms or characteristics, providing the individual with a list of topics related to the personality traits, interpersonal skills, or life skills are affected by the symptoms or characteristics, selecting a topic related to the personality traits, interpersonal skills, or life skills are affected by the symptoms or characteristics, assisting the individual in preparing a presentation on the selected topic, preparing the presentation, wherein the presentation is between ten minutes and ninety minutes in length, recording the presentation, and broadcasting the presentation.

A method of treatment for intellectual and developmental disabilities is disclosed herein, wherein the method includes the steps of diagnosing an intellectual or developmental disability in an individual, matching symptoms or characteristics associated with the individual's intellectual or developmental disability, researching what personality traits, interpersonal skills, or life skills are affected by the symptoms or characteristics, providing the individual with a list of topics related to the personality traits, interpersonal skills, or life skills are affected by the symptoms or characteristics, selecting a topic related to the personality traits, interpersonal skills, or life skills are affected by the symptoms or characteristics, assisting the individual in preparing a presentation on the selected topic, preparing the presentation, wherein the presentation is between ten minutes and ninety minutes in length, recording the presentation, and broadcasting the presentation.

A system and method for assisting a user in learning a target non-native language includes a processor executing instructions stored on a computer-readable medium, the executed instructions causing the processor to provide the user with an audible presentation of a word or a phrase in the target non-native language and prompting the user to audibly respond with speech data. The system captures the audible response and converts the audible response into input text data, then evaluates the text data for accuracy by comparing text characters in the text data to anticipated text data contained in a database. The system calculates the number of incorrect characters in the text data, then converts the evaluated text data into an output audio file and reads back the audio file to the user. The readback provided by the system provides audible feedback to the user regarding the accuracy of the evaluated text data.

A system and method for assisting a user in learning a target non-native language includes a processor executing instructions stored on a computer-readable medium, the executed instructions causing the processor to provide the user with an audible presentation of a word or a phrase in the target non-native language and prompting the user to audibly respond with speech data. The system captures the audible response and converts the audible response into input text data, then evaluates the text data for accuracy by comparing text characters in the text data to anticipated text data contained in a database. The system calculates the number of incorrect characters in the text data, then converts the evaluated text data into an output audio file and reads back the audio file to the user. The readback provided by the system provides audible feedback to the user regarding the accuracy of the evaluated text data.