Abstract: A system, method and computer program product for cognitive copy and paste. The method includes: receiving, at a hardware processor of a computer system, an input representing a selection of a content captured from a source application program, and receiving an input representing an identified target application program that will receive the selected content to be copied and rendered in the target application program. The selected content is analyzed to determine a context for the selected content; and a rendering of the selected content at a location within the destination application based on the determined context, the rendering achieving a best representation of the selected content on the destination application. The analyzing includes invoking a natural language processor to determine an intent, meaning, or an intended use of the selected content based on the determined context, and employs a support vector machine for determining a best format change when rendering.

Abstract: According to one aspect of the invention, there is provided a method for providing a voice recognition trigger, comprising the steps of: estimating a first distance, which is a distance between a device and a user, on the basis of proximity information detected by the device, and estimating a second distance, which is a distance between the device and a location where a voice detected by the device is uttered, with reference to information on the voice detected by the device; and determining whether the voice detected by the device is an object of voice recognition, with reference to similarity between the first distance and the second distance.

Abstract: A method conducts dialog between human and computer using a self-learning system. The method includes: receiving user inputs in natural language text; mapping of synonyms and key words and word mapping; analyzing the user inputs regarding sentence structure and syntax and their recognition; mapping of key phrases; determining and classifying a user intent; checking if a confirmation is required; and logically processing in a reasoning and an answer preparation with a formulation of a decision on further dialog design, formulation or the dialog history with possible generation of a response.

Abstract: A method for generating synthetic telephony narrowband data for training an automatic speech recognition model by receiving a broadband audio data file and then initiating a telephony call using a pre-configured telephone provider to play the broadband audio data file in the telephony call and to record and store audio data generated by transmission of the broadband audio data file in the telephony call, thereby generating the synthetic telephony narrowband data file from the broadband audio data file.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting utterances of a key phrase in an audio signal. One of the methods includes receiving, by a key phrase spotting system, an audio signal encoding one or more utterances; while continuing to receive the audio signal, generating, by the key phrase spotting system, an attention output using an attention mechanism that is configured to compute the attention output based on a series of encodings generated by an encoder comprising one or more neural network layers; generating, by the key phrase spotting system and using attention output, output that indicates whether the audio signal likely encodes the key phrase; and providing, by the key phrase spotting system, the output that indicates whether the audio signal likely encodes the key phrase.

Abstract: A system and apparatus are provided for generating synthetic telephony narrowband data for training an automatic speech recognition model by receiving a broadband audio data file and then initiating a telephony call using a pre-configured telephone provider to play the broadband audio data file in the telephony call and to record and store audio data generated by transmission of the broadband audio data file in the telephony call, thereby generating the synthetic telephony narrowband data file from the broadband audio data file.

Abstract: A method determines a relevancy of answers to questions based on token relevance in a system capable of answering questions. One or more processors receive a question that is composed of a set of tokens T (T1, T2, . . . , Tn). The processor(s) select tokens T? (T?1, T?2, . . . , T?m) from the tokens T (T1, T2, . . . , Tn), where each T?j from T? is a noun, and classify each T?j as a noun type. The processor(s) scan a corpus to identify passages with candidate answers to the question, and analyze the identified passages utilizing noun entries in the passages classified as the noun type. The processor(s) train an artificial intelligence (AI) system to associate a relevancy to the question for the identified passages based on noun types, and then utilize the trained AI system to provide an answer to the question based on an output of the trained AI system.

Abstract: A method, system, and computer program product include providing a list of triggers, training the natural language processor with the list of triggers, providing to the natural language processor a text including one trigger, selecting nodes in the text to create an original potential span, predicting whether the original potential span includes another trigger, and adjusting, in response to predicting that the original potential span includes another trigger, the original potential span to exclude the another trigger to create a new potential span.

Abstract: Systems and methods are set forth for identifying key-words and key-phrases, collectively referred to as key-terms, from a document. A document is accessed and the document is tokenized, each token corresponding to a word or phrase occurring within the document. Term frequencies of the terms of the tokens may be determined and TF-IDF scores may be generated according to the term frequencies. Embedding vectors for the terms of the tokens may be generated and a document embedding vector may be generated according to the embedding vectors of the documents. A similarity score may be determined for each token according to the embedding vector of a token and the document embedding vector. Additionally, an overall score may be determined for each token according to the term of the token, a TF-IDF score, similarity scores, and the like. Terms from the highest scoring tokens are selected as the key-terms for the document.

Abstract: A method includes receiving audio data encoding an utterance spoken by a native speaker of a first language, and receiving a biasing term list including one or more terms in a second language different than the first language. The method also includes processing, using a speech recognition model, acoustic features derived from the audio data to generate speech recognition scores for both wordpieces and corresponding phoneme sequences in the first language. The method also includes rescoring the speech recognition scores for the phoneme sequences based on the one or more terms in the biasing term list, and executing, using the speech recognition scores for the wordpieces and the rescored speech recognition scores for the phoneme sequences, a decoding graph to generate a transcription for the utterance.

Abstract: An audio device with at least one microphone adapted to receive sound from a sound field and create an output, and a processing system that is responsive to the output of the microphone. The processing system is configured to use a signal processing algorithm to detect a wakeup word, and modify the signal processing algorithm that is used to detect the wakeup word if the sound field changes.

Abstract: Pre-processing systems, methods of pre-processing, and speech processing systems for improved Automated Speech Recognition are provided. Some pre-processing systems for improved speech recognition of a speech signal are provided, which systems comprise a pitch estimation circuit; and a pitch equalization processor. The pitch estimation circuit is configured to receive the speech signal to determine a pitch index of the speech signal, and the pitch equalization processor is configured to receive the speech signal and pitch information, to equalize a speech pitch of the speech signal using the pitch information, and to provide a pitch-equalized speech signal.

Abstract: Systems and methods are provided for analyzing voice-based audio inputs. A voice-based audio input associated with a user (e.g., wherein the voice-based audio input is a prompt or a command) is received and measures of one or more features are extracted. One or more parameters are calculated based on the measures of the one or more features. The occurrence of one or more mistriggers is identified by inputting the one or more parameters into a predictive model. Further, systems and methods are provided for identifying human mental health states using mobile device data. Mobile device data (including sensor data) associated with a mobile device corresponding to a user is received. Measurements are derived from the mobile device data and input into a predictive model. The predictive model is executed and outputs probability values of one or more symptoms associated with the user.

Abstract: A machine accesses a preexisting set of natural language text documents in multiple natural languages. Each natural language text document in at least a portion of the preexisting set is associated with an event. The machine trains, using the preexisting set of natural language text documents and the associated events, an event encoder to learn associations between texts and event annotations. The event encoder leverages a parser in each of the two or more natural languages. The machine generates, using the event encoder, new event annotations for texts. The machine trains, using the preexisting set of natural language text documents and the new event annotations for the texts generated by the event encoder, an event extraction engine to extract events from natural language texts in the two or more natural languages. The event extraction engine leverages the parser in each of the two or more natural languages.

Abstract: A system and method that translates sentences of natural language text into sets of axioms of formal logic that are consistent with parses resulting from NLP and acquired constraints as they accumulate. The system and method further present these axioms so as to facilitate further disambiguation of such sentences and produces axioms of formal logic suitable for processing by automated reasoning technologies, such as first-order or description logic suitable for processing by various reasoning algorithms, such as logic programs, inference engines, theorem provers, and rule-based systems.

Abstract: The disclosure provides a smart liquor cabinet and a management method for the liquor cabinet. In the management method, a voice command is received and an intent of the voice command is determined. If the intent of the voice command is related to a remaining space of the liquor cabinet, then the remaining space with no liquor in the liquor cabinet is determined. If the intent of the voice command is related to an inventory situation of the liquor cabinet, then the inventory situation of stored liquor in the liquor cabinet is determined. The response of the intent is outputted. The response is related to the remaining space or the inventory situation. In this way, the liquor and space in the liquor cabinet may be counted easily and quickly.

Abstract: An information processing device includes: a first reception unit configured to receive an input of one or more characters; a second reception unit configured to receive an input of voice; and a voice recognition unit configured to recognize the voice, and output a voice recognition result beginning with the one or more characters entered into the first reception unit when the second reception unit receives the input of voice with the input of the one or more characters received by the first reception unit.

Abstract: Embodiments of the present disclosure are directed to a system, methods, and computer-readable media for facilitating stylistic expression transfers in machine translation of source sequence data. Using integrated loss functions for style transfer along with content preservation and/or cross entropy, source sequence data is processed by an autoencoder trained to reduce loss values across the loss functions at each time step encoded for the source sequence data. The target sequence data generated by the autoencoder therefore exhibits reduced loss values for the integrated loss functions at each time step, thereby improving content preservation and providing for stylistic expression transfer.

Abstract: A mistranscription generated by a speech recognition system is identified. A received utterance is matched to a first utterance member within a set of known utterance members. The matching operation matches fewer than the first plural number of words in the received utterance and the received utterance varies in a first particular manner as compared to a first word in a first slot in the first utterance member. The received utterance is sent to a mistranscription analyzer component which increments evidence that the received utterance is evidence of a mistranscription. Once the incremented evidence for the mistranscription exceeds a threshold, future received utterances containing the mistranscription are treated as though the first word was recognized.

Abstract: A dialog manager receives text data corresponding to a dialog with a user. Entities represented in the text data are identified. Context data relating to the dialog is maintained, which may include prior dialog, prior API calls, user profile information, or other data. Using the text data and the context data, an N-best list of one or more dialog models is selected to process the text data. After processing the text data, the outputs of the N-best models are ranked and a top-scoring output is selected. The top-scoring output may be an API call and/or an audio prompt.