Abstract: An information processing apparatus determines, on the basis of a speech of a user to be evaluated, a reference feature quantity representing a feature of the user's speech at normal times, acquires audio feature quantity data of a target speech to be evaluated made by the user, and evaluates the feature of the target speech on the basis of a comparison result between the audio feature quantity of the target speech and the reference feature quantity.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for contextual hotwords are disclosed. In one aspect, a method, during a boot process of a computing device, includes the actions of determining, by a computing device, a context associated with the computing device. The actions further include, based on the context associated with the computing device, determining a hotword. The actions further include, after determining the hotword, receiving audio data that corresponds to an utterance. The actions further include determining that the audio data includes the hotword. The actions further include, in response to determining that the audio data includes the hotword, performing an operation associated with the hotword.

Abstract: Disclosed are an intelligent voice recognizing method, a voice recognizing apparatus, and an intelligent computing device. The an intelligent voice recognizing method according to an embodiment of the present disclosure receives a voice, acquires a sequential start language uttered sequentially with a utterance language from the voice, and sets the sequential start language as an additional start language other than a basic start language when the sequential start language is recognized as a start language of a voice recognizing apparatus, thereby being able to authenticate a user and recognize a voice even through a seamless scheme voice that is uttered in an actual situation. According to the present disclosure, one or more of the voice recognizing device, intelligent computing device, and server may be related to artificial intelligence (AI) modules, unmanned aerial vehicles (UAVs), robots, augmented reality (AR) devices, virtual reality (VR) devices, and 5G service-related devices.

Abstract: Methods and systems for training and/or using a language selection model for use in determining a particular language of a spoken utterance captured in audio data. Features of the audio data can be processed using the trained language selection model to generate a predicted probability for each of N different languages, and a particular language selected based on the generated probabilities. Speech recognition results for the particular language can be utilized responsive to selecting the particular language of the spoken utterance. Many implementations are directed to training the language selection model utilizing tuple losses in lieu of traditional cross-entropy losses. Training the language selection model utilizing the tuple losses can result in more efficient training and/or can result in a more accurate and/or robust model—thereby mitigating erroneous language selections for spoken utterances.

Abstract: A user device configured to perform wake-up word detection in a target language.

Abstract: A method for providing a context awareness service is provided. The method includes defining a control command for the context awareness service depending on a user input, triggering a playback mode and the context awareness service in response to a user selection, receiving external audio through a microphone in the playback mode, determining whether the received audio corresponds to the control command, and executing a particular action assigned to the control command when the received audio corresponds to the control command.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to receive sensor data of an occupant of a vehicle, identify a type of mask worn by the occupant based on the sensor data, select a sound filter according to the type of mask from a plurality of sound filters stored in the memory, receive sound data, apply the selected sound filter to the sound data, and perform an operation using the filtered sound data.

Abstract: In a flow of computer actions, a computer system (110) receives a request involving a machine translation. In performing the translation (160, 238), or in using the translation in subsequent computer operations (242, 1110), the computer system takes into account known statistical relationships (310), obtained from previously accumulated click-through data (180), between a machine translation performed in a flow, the flow's portions preceding the translation, and success indicators pertaining to the flow's portion following the translation. The statistical relationships are derived by data mining of the click-through data. Further, normal actions can be suspended to use a random option to accumulate the click-through data and/or perform statistical AB testing. Other features are also provided.

Abstract: A system and method for providing real-time feedback of remote collaborative communication includes: processing first audio signals to extract first speech-related features therefrom; processing first EEG signals to extract first brain activity features therefrom; processing second audio signals to extract second speech-related features therefrom; processing second EEG signals to extract second brain activity features therefrom; processing the first and second speech-related features to determine if the speech from the first and second users exhibits positive or negative vocal entrainment; processing the first and second brain activity features to determine if the brain activity of the first and second users is aligned or misaligned; and generating feedback, on at least one display device, that indicates if the speech from the first and second users exhibits positive or negative vocal entrainment and if the brain activity of the first and second users is aligned or misaligned.

Abstract: To provide a presentation assistance device that can display keywords related to presentation materials and call attention by displaying an alert when words that are forbidden to speak are spoken. A presentation assistance device 1 comprises: a presentation material storage means 3; a keyword storage means 5 which stores a plurality of keywords related to presentation materials; a related word storage means 7 which stores one or a plurality of related words for each of the plurality of keywords; an NG word storage means 9 which stores one or a plurality of NG words for each of the plurality of keywords; a voice recognition means 11; a term determination means 15 which determines whether a voice recognition term corresponds to a related word or an NG word; and a keyword output means 17 which when the voice recognition is a related word, outputs a keyword related to the related word, and when the voice recognition term is an NG word, outputs an alert and a keyword related to the NG word.

Abstract: A phone stand includes a phone holder for coupling to a phone for conducting an audio session, the audio session including at least one voice session conducted by an application executing on the phone and a plurality of microphones including a particular microphone closer to a location where a user is expected to be positioned than other microphones. The phone stand further includes a system controller configured to: receive sound signals from the particular microphone, the sound signals comprising the user's speech; separate the sounds signals into speech signals and non-speech signals; obtain one or more input mixing attributes for the speech signals and the non-speech signals; modify the speech signals and the non-speech signals based on the one or more input mixing attributes; generate mixed signals by combining the modified speech signals and the modified non-speech signals; and send the mixed signals to the phone.

Abstract: Disclosed herein is computer technology that applies natural language processing (NLP) techniques to training data to generate information used to train a natural language generation (NLG) system to produce output that stylistically resembles the training data. In this fashion, the NLG system can be readily trained with training data supplied by a user so that the NLG system is adapted to produce output that stylistically resembles such training data. In an example, an NLP system detects a plurality of linguistic features in the training data. These detected linguistic features are then aggregated into a specification data structure that is arranged for training the NLG system to produce natural language output that stylistically resembles the training data. Parameters in the specification data structure can be linked to objects in an ontology used by the NLG system to facilitate the training of the NLG system based on the detected linguistic features.

Abstract: A machine-learning conversation listening, capturing, and analyzing system that determines instructional effectiveness is a classroom setting and a machine-learning conversation listening, capturing, and analyzing process for determining classroom instructional effectiveness are disclosed. The machine-learning conversation listening, capturing, and analyzing system and process for determining classroom instructional effectiveness relies on predetermined objective criteria and uses big data, deep learning, and redundancy to validate results.

Abstract: Power consumption for a computing device may be managed by one or more keywords. For example, if an audio input obtained by the computing device includes a keyword, a network interface module and/or an application processing module of the computing device may be activated. The audio input may then be transmitted via the network interface module to a remote computing device, such as a speech recognition server. Alternately, the computing device may be provided with a speech recognition engine configured to process the audio input for on-device speech recognition.

Abstract: A system for identifying a language in audio data includes a feature extraction module for receiving an unknown input audio data stream and dividing the unknown input audio data stream into segments. A similarity module receives the segments and receives known-language audio data models for known languages. For each segment, the similarity module performs comparisons between the segment and the known-language audio data models and generates probability values representative of the probabilities that the segment includes audio data of the known languages. A processor receives the probability values for each segment and computes an entropy value for the probabilities for each segment. If the entropy value for a segment is less than the entropy value for a previous segment, the processor terminates the comparisons prior to completing comparisons for all segments.

Abstract: Apparatus and methods for interactive voice recognition. The apparatus and methods may include a canonical phrase derivation engine configured to derive canonical phrases from voice data. The apparatus may include an input engine configured to parse utterances. The apparatus may include a knowledge extraction engine to disambiguate the utterances into words, form a sequence from the words, extract context from the sequence, pair the sequence with a phrase of the canonical phrases, merge the sequence and the phrase to form a hybrid phrase, vectorize the hybrid phrase into a vector, and feed the vector into a non-linear classification engine to determine an intent corresponding to the utterances.

Abstract: Techniques for named-entity recognition are described. An exemplary implementation of a method includes extracting character features for each word of the document using a first encoder; extracting word level representations of for each word position using a second encoder, the word level representations being a concatenation of spelling variants; classifying the word level representations according to a first decoder; and outputting the classifications as named-entity labels.

Abstract: A system for identifying a language in audio data includes a feature extraction module for receiving an unknown input audio data stream and dividing the unknown input audio data stream into segments. A similarity module receives the segments and receives known-language audio data models for known languages. For each segment, the similarity module performs comparisons between the segment and the known-language audio data models and generates probability values representative of the probabilities that the segment includes audio data of the known languages. A processor receives the probability values for each segment and computes an entropy value for the probabilities for each segment. If the entropy value for a segment is less than the entropy value for a previous segment, the processor terminates the comparisons prior to completing comparisons for all segments.

Abstract: An interaction system that provides an interaction interface comprising: a computer and a device that obtains information, wherein the computer stores information for managing data in which a type of a second feature value is associated with a listening pattern that defines a tendency of a response action performed by the interaction interface on a user; calculates a first feature value that is an index for evaluating a change in state during speech by the user on the basis of information obtained by the device; calculates second feature values on the basis of the first feature value; selects a target second feature value from among the second feature values; selects the listening pattern corresponding to the target second feature value; and generates output information for controlling the interaction interface on the basis of the selected listening pattern.

Abstract: A speech recognition method, performed by a computer, with an improved recognition accuracy is disclosed. The method includes: performing speech recognition of an input speech to acquire a plurality of recognition candidates through a plurality of speech recognition processes different from each other for a section having a reliability lower than a predetermined value; verifying similarities between each of the acquired plurality of recognition candidates and meta-information corresponding to the input speech; and determining, based on the verified similarities, a recognition result of the low-reliability section from among the acquired plurality of recognition candidates.