Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for performing speaker verification. A system configured to practice the method receives a request to verify a speaker, generates a text challenge that is unique to the request, and, in response to the request, prompts the speaker to utter the text challenge. Then the system records a dynamic image feature of the speaker as the speaker utters the text challenge, and performs speaker verification based on the dynamic image feature and the text challenge. Recording the dynamic image feature of the speaker can include recording video of the speaker while speaking the text challenge. The dynamic feature can include a movement pattern of head, lips, mouth, eyes, and/or eyebrows of the speaker. The dynamic image feature can relate to phonetic content of the speaker speaking the challenge, speech prosody, and the speaker's facial expression responding to content of the challenge.

Abstract: A computer program product for use with dictated medical patient information resides on a computer-readable medium and comprises computer-readable instructions for causing a computer to analyze the dictated information, identify likely confidential information in the dictated medical patient information, and treat the likely confidential information disparately from likely non-confidential information in the dictated medical patient information.

Abstract: Aspects of the disclosure provide systems and methods for facilitating dictation. Speech input may be provided to an audio input device of a computing device. A speech recognition engine at the computing device may obtain text corresponding to the speech input. The computing device may transmit the text to a remotely-located storage device. A login webpage that includes a session identifier may be accessed from a target computing device also located remotely relative to the storage device. The session identifier may be transmitted to the storage device and, in response, a text display webpage may be received at the target computing device. The text display webpage may include the speech-derived text and may be configured to automatically copy the text to a copy buffer of the target computing device. The speech-derived text may also be provided to native applications at target computing devices or NLU engines for natural language processing.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for processing audio. A system configured to practice the method monitors, via a processor of a computing device, an image feed of a user interacting with the computing device and identifies an audio start event in the image feed based on face detection of the user looking at the computing device or a specific region of the computing device. The image feed can be a video stream. The audio start event can be based on a head size, orientation or distance from the computing device, eye position or direction, device orientation, mouth movement, and/or other user features. Then the system initiates processing of a received audio signal based on the audio start event. The system can also identify an audio end event in the image feed and end processing of the received audio signal based on the end event.

Abstract: According to some aspects, a method of searching for content in response to a user voice query is provided. The method may comprise receiving the user voice query, performing speech recognition to generate N best speech recognition results comprising a first speech recognition result, performing a supervised search of at least one content repository to identify one or more supervised search results using one or more classifiers that classify the first speech recognition result into at least one class that identifies previously classified content in the at least one content repository, performing an unsupervised search of the at least one content repository to identify one or more unsupervised search results, wherein performing the unsupervised search comprises performing a word search of the at least one content repository, and generating combined results from among the one or more supervised search results and the one or more unsupervised search results.

Abstract: An assignment device (1) assigns word class information (WKI) to one or more words of text information (ETI). Based on word-class sequence information (WK-AI) formed from this assigned word class information (WKI), actions (A) are executed in order to notify the user of conflicts or to provide the user with background information (HI) relating to words in the text information (TT).

Abstract: A system and method for generating a self-steering beamformer is provided. Embodiments may include receiving, at one or more microphones, a first audio signal and adapting one or more blocking filters based upon, at least in part, the first audio signal. Embodiments may also include generating, using the one or more blocking filters, one or more noise reference signals. Embodiments may further include providing the one or more noise reference signals to an adaptive interference canceller to reduce a beamformer output power level.

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.