Abstract: Gain mismatch and related problems can be solved by a system and method that applies an automatic microphone signal gain equalization without any direct absolute reference or calibration phase. The system and method performs the steps of receiving, by a computing device, a speech signal from a speaking person via a plurality of microphones, determining a speech signal component in the time-frequency domain for each microphone of the plurality of microphones, calculating an instantaneous cross-talk coupling matrix based on the speech signal components across the microphones, estimating gain factors based on calculated cross-talk couplings and a given expected cross-talk attenuation, limiting the gain factors to appropriate maximum and minimum values, and applying the gain factors to the speech signal used in the control path to control further speech enhancement algorithms or used in the signal path for direct influence on the speech enhanced audio output signal.

Abstract: Techniques for adapting a trained neural network acoustic model, comprising using at least one computer hardware processor to perform: generating initial speaker information values for a speaker; generating first speech content values from first speech data corresponding to a first utterance spoken by the speaker; processing the first speech content values and the initial speaker information values using the trained neural network acoustic model; recognizing, using automatic speech recognition, the first utterance based, at least in part on results of the processing; generating updated speaker information values using the first speech data and at least one of the initial speaker information values and/or information used to generate the initial speaker information values; and recognizing, based at least in part on the updated speaker information values, a second utterance spoken by the speaker.

Abstract: In some embodiments, a system is provided comprising at least one processor programmed to process an input text to identify a plurality of semantic patterns that match the input text, wherein, for at least one semantic pattern of the plurality of semantic patterns: the at least one semantic pattern comprises a plurality of semantic entities identified from the at least one input text, and the plurality of semantic entities occur in a common context within the at least one input text. The at least one processor may be further programmed to use statistical information derived from training data to associate a respective weight with each semantic pattern of the plurality of semantic patterns.

Abstract: A method and a system for generating, with the assistance of a computer system (12), a medical report (18) suitable for automatic billing, where an electronic template (39) suited for a specific patient's condition is selected out of a plurality of given electronic templates stored in storage means (15); personal data of the specific patient's and previously stored in storage means (11) are automatically entered into the selected electronic template; and medical report text passages and instructions are entered into the selected template by dictating and using a speech recognition system (13); additionally, condition data are automatically entered on the basis of condition information as far as stored in storage means (7) into the selected template, and code data associated with these condition information are automatically embedded in the selected template; and when entering medical report text passages, at least one predetermined voice macro stored in the storage means (16) together with code data embedded

Abstract: A method, computer program product, and computing system for monitoring a portion of speech on an automated speech recognition system that includes a plurality of classifiers, thus defining a monitored portion of speech, wherein an operation is defined for each of the plurality of classifiers. A confidence score concerning the monitored portion of speech is associated with each of a plurality of classifiers, thus defining a plurality of confidence scores. If one of the plurality of confidence scores is an acceptable confidence score, the operation defined for the classifier associated with the acceptable confidence score is effectuated.

Abstract: Techniques for presenting alternative hypotheses for medical facts may include identifying, using at least one statistical fact extraction model, a plurality of alternative hypotheses for a medical fact to be extracted from a portion of text documenting a patient encounter. At least two of the alternative hypotheses may be selected, and the selected hypotheses may be presented to a user documenting the patient encounter.

Abstract: Disclosed methods and systems are directed to generating ontological relationships. The methods and systems may include receiving a set of words comprising one or more verbs and a plurality of nouns and determining one or more first ontological relationships between the plurality of nouns based on an association of each of the nouns with at least one of the one or more verbs; and a correspondence between one or more glosses associated with each of the plurality of nouns. The methods and systems may include receiving an input associated with the one or more first ontological relationships, and determining, based on the input, one or more second ontological relationships between the plurality of nouns.

Abstract: A method, computer program product, and computing system for receiving content from a third-party. The content may be processed to predict the disclosure of sensitive information. The sensitive information may be obscured from a platform user, where the third-party may be a customer and the platform user may be a customer service representative.

Abstract: In some natural language understanding (NLU) applications, results may not be tailored to the user's query. In an embodiment of the present invention, a method includes tagging elements of automated speech recognition (ASR) data based on an ontology stored in a memory. The method further includes indexing tagged elements to an entity of the ontology. The method further includes generating a logical form of the ASR data based on the tagged elements and the indexed entities. The method further includes mapping the logical form to a query to a respective corresponding database stored in the memory. The method further includes issuing the query to the respective corresponding databases. The method further includes presenting results of the query to the user via a display or a voice response system.

Abstract: Disclosed methods and systems are directed to determining a best microphone pair and segmenting sound signals. The methods and systems may include receiving a collection of sound signals comprising speech from one or more audio sources (e.g., meeting participants) and/or background noise. The methods and systems may include calculating a TDOA and determining, based on the TDOA and via robust statistics, the best pair of microphones. The methods and systems may also include segmenting sound signals from multiple sources.

Abstract: Disclosed herein are systems, computer-implemented methods, and tangible computer-readable media for placing an order for a user. The method includes receiving a search from a user, identifying a product category based on the search, presenting to the user a general ordering screen based on the identified product category, selecting and activating a speech recognition grammar tuned for the identified product category, recognizing a first received user utterance with the activated tuned grammar to identify a vendor who offers items in the identified product category, recognizing a second received user utterance with the activated tuned grammar to identify a specific item from the identified vendor, and placing an order for the specific item with the identified vendor for the user. In one aspect, the method further offers to sell the user additional items ancillary to the specific item.

Abstract: The method comprises receive first audio comprising speech from a user of a computing device, detecting an end of speech in the first audio, generating an ASR result based, at least in part, on a portion of the first audio prior to the detected end of speech, determining whether a valid action can be performed by a speech-enabled application installed on the computing device using the ASR result, and processing second audio when it is determined that a valid action cannot be performed by the speech-enabled application using the ASR result.

Abstract: According to some aspects, a method for aligning a first data source and a second data source during a plurality of iterations comprising a current iteration and a previous iteration is provided. The method comprises generating at least one property alignment hypothesis between at least one first property of the first data source and at least one second property of the second data source; generating a plurality of instance alignment hypotheses between a respective first plurality of instances of the first data source and a respective second plurality of instances of the second data source; and verifying at least one property alignment hypothesis and/or at least one of the plurality of instance alignment hypotheses. Generating the at least one property alignment hypothesis and/or generating the plurality of instance alignment hypotheses is based, at least in part, on at least one property alignment hypothesis and/or at least one instance alignment hypothesis verified during the previous iteration.

Abstract: Methods and apparatus for natural language understanding (NLU) processing based on user-specified interests. Information specifying a weight for each of a plurality of domains is received via a user interface. The plurality of domains each relates to a potential area of interest for the user, and the weight for a domain from among the plurality of domains indicates a level of interest for the user in the domain. A ranking classifier used to rank NLU hypotheses generated by an NLU engine is trained using training data from which features are, at least in part, based on the information specifying a weight for each of the plurality of domains.

Abstract: A method of verifying a user identity using a Web-based multimodal interface can include sending, to a remote computing device, a multimodal markup language document that, when rendered by the remote computing device, queries a user for a user identifier and causes audio of the user's voice to be sent to a multimodal, Web-based application. The user identifier and the audio can be received at about a same time from the client device. The audio can be compared with a voice print associated with the user identifier. The user at the remote computing device can be selectively granted access to the system according to a result obtained from the comparing step.

Abstract: A method, computer program product, and computing system for obtaining encounter information of a patient encounter, wherein the encounter information includes machine vision encounter information; processing the machine vision encounter information to identify one or more humanoid shapes; and steering one or more audio recording beams toward the one or more humanoid shapes to capture audio encounter information.

Abstract: An ontology stores information about a domain of an automatic speech recognition (ASR) application program. The ontology is augmented with information that enables subsequent automatic generation of a speech understanding grammar for use by the ASR application program. The information includes hints about how a human might talk about objects in the domain, such as preludes (phrases that introduce an identification of the object) and postludes (phrases that follow an identification of the object).

Abstract: Methods described herein provide functionality for automatic speech recognition (ASR). One such embodiment performs speech recognition using received speech recognition result candidates, where the received candidates were generated by performing Statistical Language Model (SLM) based speech recognition on one or more frames of audio data. In turn, such an embodiment transmits results of the speech recognition, performed using the received speech recognition result candidates, to a user device via a communications network. Results of the speech recognition are available with lower latency than pure cloud based ASR solution.

Abstract: A method of providing a task assistant to provide an interface to an application, the method comprising activating the task assistant, the activation having an associated visual display. The method in one embodiment includes receiving input from a user through multimodal input including a plurality of speech input, typing input, and touch input, interpreting the input, and providing a formatted query to the application, receiving data from the application in response to the query, and providing a response to the user through multimodal output including a plurality of: speech output, text output, non-speech audio output, haptic output, and visual non-text output, wherein the task assistant has a plurality of active states, each of the active states having an associated visual display.

Abstract: Cascaded models may be applied to extract facts from a medical text. A first model may be applied to at least a portion of the medical text. The first model extracts at least one first medical fact. The at least one first medical fact is linked to at least first text in the at least a portion of the medical text. A second model may be applied to the first text. The second model extracts at least one second fact that is an attribute of the at least one first medical fact.