Abstract: A system for administering performance tests to patients remotely has a server that can execute one or more performance tests, presented to the patient via a virtual agent running on the patient's computing device. The performance tests ask the patient to perform a task and then the patient's computing device captures the performance of the task such that the server can analyze the results and determine whether the patient suffers from a condition. The system is capable of adapting based on how a patient performs the tests, whether additional tests are needed or due to technical difficulties.

Abstract: A system and method for remote monitoring of patient motor functions includes a computing device that uses captured image data depicting a patient's body part and, based on movement information, detects whether a condition may exist that is affecting motor functions. The body part can be a hand that is tracked as the user performs a tapping exercise. The body part can also include the patient's face during speech and also without speech.

Abstract: A virtual agent instructs a responding person to perform specific verbal exercises. Audio and image inputs from the responding person's performance of the exercises are used to identify speech, video, cognitive, and/or respiratory biomarkers, which are then used to evaluate speech motor function and/or neurological health. Contemplated exercises include test aspects of oral motor proficiency, sustained phonation, diadochokinesis, reading speech, spontaneous speech, spirometry, picture description, and emotion elicitation. Metrics from evaluation of the responding person's performance are advantageously produced automatically, and are presented in spreadsheet format.

Abstract: A computer-generated dialog session is customized for a user having a pathology characterized at least in part by a speech pathology. The user's speech is analyzed for spans of speech in which the starts and ends of the spans satisfy predetermined thresholds of time. Customization occurs by altering at least one of the following configurable parameters: (a) a threshold minimum signal strength of speech (dB) to consider as the start of the span of speech; (b) an adjustment factor by which signal strengths of background noise increases between consecutive spans of speech; (c) a threshold between signal strength during the span of speech and signal strength during the span of non-speech; (d) a start speech time threshold; and (e) an end speech time threshold.

Abstract: Aspects described herein provide quality assurance checks for improving the construction of natural language understanding grammars. An annotation module may obtain a set of annotations for a set of text samples based, at least in part, on an ontology and a grammar. A quality assurance module may automatically perform one or more quality assurance checks on the set of annotations, the ontology, the grammar, or combinations thereof. The quality assurance module may generate a list of flagged annotations during performance of a quality assurance check. The list of flagged annotations may be presented at an annotation review interface displayed at a display device. One of the flagged annotations may be selected and presented at an annotation interface displayed at the display device. Responsive to presentation of the flagged annotation, the ontology, the grammar, the flagged annotation selected, or combinations thereof may be updated based on user input received.

Abstract: Aspects described herein provide quality assurance checks for improving the construction of natural language understanding grammars. An annotation module may obtain a set of annotations for a set of text samples based, at least in part, on an ontology and a grammar. A quality assurance module may automatically perform one or more quality assurance checks on the set of annotations, the ontology, the grammar, or combinations thereof. The quality assurance module may generate a list of flagged annotations during performance of a quality assurance check. The list of flagged annotations may be presented at an annotation review interface displayed at a display device. One of the flagged annotations may be selected and presented at an annotation interface displayed at the display device. Responsive to presentation of the flagged annotation, the ontology, the grammar, the flagged annotation selected, or combinations thereof may be updated based on user input received.

Abstract: Aspects described herein provide quality assurance checks for improving the construction of natural language understanding grammars. An annotation module may obtain a set of annotations for a set of text samples based, at least in part, on an ontology and a grammar. A quality assurance module may automatically perform one or more quality assurance checks on the set of annotations, the ontology, the grammar, or combinations thereof. The quality assurance module may generate a list of flagged annotations during performance of a quality assurance check. The list of flagged annotations may be presented at an annotation review interface displayed at a display device. One of the flagged annotations may be selected and presented at an annotation interface displayed at the display device. Responsive to presentation of the flagged annotation, the ontology, the grammar, the flagged annotation selected, or combinations thereof may be updated based on user input received.

Abstract: A system and method for localizing a spoken dialog system is disclosed. Source data from a source language spoken dialog system is accessed, including semantic annotations and transcriptions of a plurality of utterances. The transcriptions are machine-translated into a target language. Semantic classifiers are trained on the machine translated transcriptions and the source language semantic annotations.

Abstract: Aspects described herein provide quality assurance checks for improving the construction of natural language understanding grammars. An annotation module may obtain a set of annotations for a set of text samples based, at least in part, on an ontology and a grammar. A quality assurance module may automatically perform one or more quality assurance checks on the set of annotations, the ontology, the grammar, or combinations thereof. The quality assurance module may generate a list of flagged annotations during performance of a quality assurance check. The list of flagged annotations may be presented at an annotation review interface displayed at a display device. One of the flagged annotations may be selected and presented at an annotation interface displayed at the display device. Responsive to presentation of the flagged annotation, the ontology, the grammar, the flagged annotation selected, or combinations thereof may be updated based on user input received.

Abstract: A dialog manager for a spoken dialog system. A decision module selects a path from a plurality of alternative paths for a given call, wherein each path implements one of a plurality of strategies for a call flow. A weighting module weights the path selection decision and is connected to a probability estimator for estimating the probability value that a given one of the plurality of paths is the best-performing path.

Abstract: A system and a method to generate statistical utterance classifiers optimized for the individual states of a spoken dialog system is disclosed. The system and method make use of large databases of transcribed and annotated utterances from calls collected in a dialog system in production and log data reporting the association between the state of the system at the moment when the utterances were recorded and the utterance. From the system state, being a vector of multiple system variables, subsets of these variables, certain variable ranges, quantized variable values, etc. can be extracted to produce a multitude of distinct utterance subsets matching every possible system state. For each of these subset and variable combinations, statistical classifiers can be trained, tuned, and tested, and the classifiers can be stored together with the performance results and the state subset and variable combination.

Abstract: A method and apparatus for continuously improving the performance of semantic classifiers in the scope of spoken dialog systems are disclosed. Rule-based or statistical classifiers are replaced with better performing rule-based or statistical classifiers and/or certain parameters of existing classifiers are modified. The replacement classifiers or new parameters are trained and tested on a collection of transcriptions and annotations of utterances which are generated manually or in a partially automated fashion. Automated quality assurance leads to more accurate training and testing data, higher classification performance, and feedback into the design of the spoken dialog system by suggesting changes to improve system behavior.

Abstract: A single, subjective numerical rating to evaluate the performance of a telephone-based spoken dialog system. This CE rating is provided by expert human listeners who have knowledge of the design of the dialog system. Different human raters can be trained to achieve a satisfactory level of agreement. Furthermore, a classifier trained on ratings by human experts can reproduce the human ratings with the same degree of consistency. More calls can be given a CE rating than would be possible with limited human resources. More information can be provided about individual calls, e.g., to help decide between two disparate ratings by different human experts.

Abstract: A dialog manager for a spoken dialog system. A decision module selects a path from a plurality of alternative paths for a given call, wherein each path implements one of a plurality of strategies for a call flow. A weighting module weights the path selection decision and is connected to a probability estimator for estimating the probability value that a given one of the plurality of paths is the best-performing path.

Abstract: A system and method for localizing a spoken dialog system is disclosed. Source data from a source language spoken dialog system is accessed, including semantic annotations and transcriptions of a plurality of utterances. The transcriptions are machine-translated into a target language. Semantic classifiers are trained on the machine translated transcriptions and the source language semantic annotations.

Abstract: A system and a method to generate statistical utterance classifiers optimized for the individual states of a spoken dialog system is disclosed. The system and method make use of large databases of transcribed and annotated utterances from calls collected in a dialog system in production and log data reporting the association between the state of the system at the moment when the utterances were recorded and the utterance. From the system state, being a vector of multiple system variables, subsets of these variables, certain variable ranges, quantized variable values, etc. can be extracted to produce a multitude of distinct utterance subsets matching every possible system state. For each of these subset and variable combinations, statistical classifiers can be trained, tuned, and tested, and the classifiers can be stored together with the performance results and the state subset and variable combination.

Abstract: A method and apparatus for continuously improving the performance of semantic classifiers in the scope of spoken dialog systems are disclosed. Rule-based or statistical classifiers are replaced with better performing rule-based or statistical classifiers and/or certain parameters of existing classifiers are modified. The replacement classifiers or new parameters are trained and tested on a collection of transcriptions and annotations of utterances which are generated manually or in a partially automated fashion. Automated quality assurance leads to more accurate training and testing data, higher classification performance, and feedback into the design of the spoken dialog system by suggesting changes to improve system behavior.

Abstract: A single, subjective numerical rating to evaluate the performance of a telephone-based spoken dialog system is disclosed. This CE rating is provided by expert human listeners who have knowledge of the design of the dialog system. Different human raters can be trained to achieve a satisfactory level of agreement. Furthermore, a classifier trained on ratings by human experts can reproduce the human ratings with the same degree of consistency. More calls can be given a CE rating than would be possible with limited human resources. More information can be provided about individual calls, e.g., to help decide between two disparate ratings by different human experts.