Abstract: A method, computer program product, and computer system for receiving, by a computing device, a first signal emitted from one or more sources. A second signal may be received emitted from the one or more sources. A first confidence level that the wake-up-word is included in the first signal may be determined. A second confidence level that the wake-up-word is included in the second signal may be determined. It may be identified that the wake-up-word originated from a first source of the one or more sources based upon, at least in part, the first and second confidence levels. The first source may be enabled to participate in a dialog phase. The second source may be excluded from participating in the dialog phase.

Abstract: Methods and apparatus for voice-enabling a web application, wherein the web application includes one or more web pages rendered by a web browser on a computer. At least one information source external to the web application is queried to determine whether information describing a set of one or more supported voice interactions for the web application is available, and in response to determining that the information is available, the information is retrieved from the at least one information source. Voice input for the web application is then enabled based on the retrieved information.

Abstract: Methods and apparatus for communicating between virtual agents associated with users of electronic devices connected via at least one network. A first user may instruct an associated first virtual agent to invoke a communication session with a second virtual agent associated with a second user. To invoke the communication session, the first virtual agent may send an outgoing communication to the second virtual agent and the outgoing communication may instruct the second virtual agent to perform at least one action on behalf of the first user. Virtual agents associated with different users may alternatively communicate with each other in the absence of user interaction to perform a collaborative action.

Abstract: A system is provided, comprising at least one processor and at least one computer-readable storage medium. The at least one computer-readable storage medium may store a plurality of point-of-interest segment indices. The at least one computer-readable storage medium may further store instructions which program the at least one processor to: match a first text segment to a first point-of-interest segment index stored in the at least one computer-readable storage medium; match a second text segment to a second point-of-interest segment index stored in the at least one computer-readable storage medium; and use the first and second point-of-interest segment indices to identify one or more candidate point-of-interest entries matching both the first and second text segments.

Abstract: Devices and systems supporting more than one Virtual Assistant (VA) are able to initiate and collaborate with multiple virtual assistants within the same session and at the same time. This system allows application specific virtual assistants to register and listen for intents from a general purpose virtual assistant. When the general purpose virtual assistant raises an intent, control can be passed to an interested application specific virtual assistant for handling. The system of registering new intents increases the knowledge of the general purpose virtual assistant, or overloads the handling of an existing intent.

Abstract: A system and method for acoustic echo cancellation is provided. Embodiments may include receiving, at one or more microphones, an audio reference signal from an audio speaker. Embodiments may also include filtering the audio reference signal using one or more adaptive audio filters. Embodiments may further include analyzing a level of signal energy of the audio reference signal with regard to time, frequency and audio channel to identify at least one maximum error contribution point. Embodiments may also include updating the one or more adaptive audio filters based upon, at least in part, the analyzed audio reference signal.

Abstract: In a method for validating data, a text of a document is received. At least one fact is extracted from the text. At least one expert refinement is merged with the at least one fact to create at least one modified fact. The at least one modified fact is provided for a review. An expert refinement to the at least one modified fact is captured in response to the review. A superset document based on the at least one pre-existing refinement and the expert refinement is stored.

Abstract: In a method for validating data, a text of a document is received. At least one fact is extracted from the text. At least one expert refinement is merged with the at least one fact to create at least one modified fact. The at least one modified fact is provided for a review. An expert refinement to the at least one modified fact is captured in response to the review. A superset document based on the at least one pre-existing refinement and the expert refinement is stored.

Abstract: A method is provided for representing and updating the state of a dialog involving a series of queries and commands to an artificial intelligence system. Each statement within the dialogue may be modeled as a relational tree spanning nodes corresponding to named entities within the statement. A data structure may be used to store each of these trees and to modify them as the dialog progresses. A subsequent statement in the dialog may be parsed and its contents used to update an ongoing search initiated within that dialog. Statements may be used for the update process despite being fragmentary or not corresponding to any predetermined grammar. An algorithm is disclosed for updating the trees within the data structure after a new statement is parsed.

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: 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: Aspects of the disclosure are directed to natural language processing. An input interface of a computing device receives input (e.g., speech input) and generates a digital signal corresponding to that input. Text corresponding to the digital signal is obtained, and the text is processed using each of a context-free and a context-specific linguistic model to generate linguistic processing results for that text. The text and linguistic processing results may be processed using a NLU model to generate an NLU recognition result corresponding to the input received at the input interface. The text and the linguistic processing results may also be annotated and used to train a NLU model. The linguistic processing results may relate to, e.g., the tokenization of portions of the text, the normalization of portions of the text, sequences of normalizations for portions of the text, and rankings and prioritization of the linguistic processing results.

Abstract: Methods and apparatus for using visual information to facilitate a speech recognition process. The method comprises dividing received audio information into a plurality of audio frames, determining for each of the plurality of audio frames, whether the audio information in the audio frame comprises speech from the foreground speaker, wherein the determining is based, at least in part, on received visual information, and transmitting the audio frame to an automatic speech recognition (ASR) engine for speech recognition when it is determined that the audio frame comprises speech from the foreground speaker.

Abstract: An original text that is a representation of a narration of a patient encounter provided by a clinician may be received and re-formatted to produce a formatted text. One or more clinical facts may be extracted from the formatted text. A first fact of the clinical facts may be extracted from a first portion of the formatted text, and the first portion of the formatted text may be a formatted version of a first portion of the original text. A linkage may be maintained between the first fact and the first portion of the original text.

Abstract: Techniques for generating language models. The techniques include: obtaining language data comprising training data and associated values for one or more metadata attributes, the language data comprising a plurality of instances of language data, an instance of language data comprising an instance of training data and one or more metadata attribute values associated with the instance of training data; identifying, by processing the language data using at least one processor, a set of one or more of the metadata attributes to use for clustering the instances of training data into a plurality of clusters; clustering the training data instances based on their respective values for the identified set of metadata attributes into the plurality of clusters; and generating a language model for each of the plurality of clusters.

Abstract: According to some aspects, a method of training a transformation component using a trained acoustic model comprising first parameters having respective first values established during training of the acoustic model using first training data is provided. The method comprises using at least one computer processor to perform coupling the transformation component to a portion of the acoustic model, the transformation component comprising second parameters, and training the transformation component by determining, for the second parameters, respective second values using second training data input to the transformation component and processed by the acoustic model, wherein the acoustic model retains the first parameters having the respective first values throughout training of the transformation component.

Abstract: Methods and apparatus for processing a voicemail message to generate a textual representation of at least a portion of the voicemail message. At least one emotion expressed in the voicemail message is determined by applying at least one emotion classifier to the voicemail message and/or the textual representation. An indication of the determined at least one emotion is provided in a manner associated with the textual representation of the at least a portion of the voicemail message.

Abstract: Speech recorded by an audio capture facility of a music facility is processed by a speech recognition facility to generate results that are provided to the music facility. When information related to a music application running on the music facility are provided to the speech recognition facility, the results generated are based at least in part on the application related information. The speech recognition facility uses an unstructured language model for generating results. The user of the music facility may optionally be allowed to edit the results being provided to the music facility. The speech recognition facility may also adapt speech recognition based on usage of the results.

Abstract: Techniques for combining the results of multiple recognizers in a distributed speech recognition architecture. Speech data input to a client device is encoded and processed both locally and remotely by different recognizers configured to be proficient at different speech recognition tasks. The client/server architecture is configurable to enable network providers to specify a policy directed to a trade-off between reducing recognition latency perceived by a user and usage of network resources. The results of the local and remote speech recognition engines are combined based, at least in part, on logic stored by one or more components of the client/server architecture.

Abstract: A system and method for speech recognition is provided. Embodiments may include receiving, at a first computing device, a far-talk signal from a far-talk computing device, the far-talk signal transmitted using a first channel and corresponding to an audible sound. Embodiments may further include receiving, at the first computing device, a near-talk signal from a near-talk computing device, the near-talk signal transmitted using a second channel and corresponding to the audible sound, wherein the far-talk signal and the near-talk signal are received during an enrollment phase of a far-talk speech recognition system. Embodiments may also include updating, at the first computing device, one or more models associated with a far-talk speech recognition system based upon, at least in part, one or more characteristics of the far-talk signal and one or more characteristics of the near-talk signal.