Abstract: Disclosed is a device and method for diffusing a therapeutic specific to a user's emotional/mental state (EMS), comprising the steps of: selecting (or assessing) at least one EMS, said selected (or assessed) EMS indicating at least one of an emotion, mental, and/or physical state of the user; and activating the ultrasonic membrane of the at least single reservoir (optionally, a plurality of reservoirs) housing the mist specific to the selected/assessed EMS, wherein said activation results in a vibration of the membrane causing an ultra-sonic frequency resulting in the atomization and diffusion of the prescribed mist based on the user-selected (or assessed) EMS.

Abstract: An electronic device and method are disclosed. The device includes a memory and speech recognition circuitry and/or a processor, which implements the method, including: receiving a first utterance, and processing the first utterance to initiate a session and generate a first response result, after the session related to the first utterance is terminated, receiving a second utterance, processing the second utterance to generate a second response result, based on the second response result, determining whether to execute follow-up utterance processing on the second utterance as if the session were active, based on determining to execute the follow-up utterance processing, reprocessing the second utterance based at least in part on the first response result related to the first utterance to generate a third response result, and outputting the third response result.

Abstract: AM and LM parameters to be used for adapting an ASR model are derived for each audio segment of an audio stream comprising multiple audio programs. A set of identifiers, including a speaker identifier, a speaker domain identifier and a program domain identifier, is obtained for each audio segment. The set of identifiers are used to select most suitable AM and LM parameters for the particular audio segment. The embodiments enable provision of maximum constraints on the AMs and LMs and enable adaptation of the ASR model on the fly for audio streams of multiple audio programs, such as broadcast audio. This means that the embodiments enable selecting AM and LM parameters that are most suitable in terms of ASR performance for each audio segment.

Abstract: A system configured to perform directional speech separation. The system may dynamically associate direction-of-arrivals with one or more audio sources in order to generate output audio data that separates each of the audio sources. The system identifies a target direction for each audio source, dynamically determines directions that are correlated with the target direction, and generates output signals for each audio source. The system may associate individual frequency bands with specific directions based on a time delay detected by two or more microphones. The system may determine a cross-correlation between each direction and the target direction and select directions with strong correlation. The system may generate time-frequency mask data indicating frequency bands corresponding to the directions associated with a particular audio source. Using the mask data, the system generates output audio data specific to the audio source, resulting in directional speech separation between different audio sources.

Abstract: An apparatus and method are disclosed for processing an audio signal. The apparatus includes an input interface, a digital filterbank having an analysis part and a synthesis part, a first phase shifter, a spectral envelope adjuster, a second phase shifter, and an output interface. The first phase shifter and the second phase shifter reduce a complexity of the digital filterbank, which includes both analysis and synthesis filters that are complex-exponential modulated versions of a prototype filter.

Abstract: Techniques for disambiguating which profile, of multiple profiles, is to be used to respond to a user input are described. A device located in a communal space (e.g., a hotel room or suite of rooms, conference room, hospital room, etc.) may be associated with a device profile and a user profile of a user presently occupying the communal space. When the user inputs a command to the device (either by text or speech), a system associated with the device determines the profiles (e.g., a device profile and a user profile) associated with the device. The system determines one or more policies associated with the device. The one or more policies may correspond to rules for disambiguating which profile to use to execute with respect to the user input. Using the one or more policies, the system determines which profile is to be used, and causes a speechlet component to execute using information specific to the determined profile.

Abstract: During text-to-speech processing, a speech model creates output audio data, including speech, that corresponds to input text data that includes a representation of the speech. A spectrogram estimator estimates a frequency spectrogram of the speech; the corresponding frequency-spectrogram data is used to condition the speech model. A plurality of acoustic features corresponding to different segments of the input text data, such as phonemes, syllable-level features, and/or word-level features, may be separately encoded into context vectors; the spectrogram estimator uses these separate context vectors to create the frequency spectrogram.

Abstract: Providing cognitive responses with an electronic message system includes predicting an urgency level corresponding to an electronic message received by the system based on detecting pre-defined features within the message and assigning a classification to the message based on the detected features. The message and corresponding urgency level can be mapped to a response action based on the classification assigned to the message. A notification of the response action and corresponding urgency level can be generated.

Abstract: A method of modelling speech of a user of a headset comprising a microphone, the method comprising: receiving a first sample, from a bone-conduction sensor, representing bone-conducted speech of the user; obtaining a measure of fundamental frequency of the bone-conducted speech in each of a plurality of speech frames of the first sample; obtaining a first distribution of the fundamental frequencies of the bone-conducted speech over the plurality of speech frames; receiving, from the microphone, a second sample; determining a first acoustic condition at the headset based on the second signal; performing a biometric process based on the first distribution of fundamental frequencies and the first acoustic condition.

Abstract: Methods for voice authentication include receiving a plurality of mono telephonic interactions between customers and agents; creating a mapping of the plurality of mono telephonic interactions that illustrates which agent interacted with which customer in each of the interactions; determining how many agents each customer interacted with; identifying one or more customers an agent has interacted with that have the fewest interactions with other agents; and selecting a predetermined number of interactions of the agent with each of the identified customers. In some embodiments, the methods further include creating a voice print from first and second speaker components of each interaction; comparing the voice prints of a first selected interaction to the voice prints from a second selected interaction; calculating a similarity score between the voice prints; aggregating scores; and identifying the voice prints that are associated with the agent.

Abstract: A hearing apparatus includes: a receiving unit configured to obtain a first speech signal; a processor configured to provide of an electrical output signal based on the first speech signal; and a receiver for providing an audio output signal based on the electrical output signal; wherein the hearing apparatus is configured to determine a first word count of the first speech signal, and update a total word count based on the first word count.

Abstract: Various embodiments relate generally to data science and data analysis, computer software and systems, and control systems to provide a platform to facilitate implementation of an interface, and, more specifically, to a computing and data storage platform that implements specialized logic to predict effectiveness of content in electronic messages as a function, for example, modifiable portions of the content. In some examples, a method may include receiving data signals to cause formation of an electronic message, determining a component of the electronic message, identifying one or more message performance criteria, characterizing the component to identify a component attribute, predicting the component attribute matches at least one of the message performance criteria, and transmitting the electronic message.

Abstract: A process for interfacing with an electronic communications device including a single input interface (SII) for accessing an electronic digital assistant and voice control includes detecting a first activation of the SII, and responsively playing back a first audio feedback indicative of activation of a voice input function. Then monitoring for one of two or more pre-configured voice control keywords, a first associated with a local electronic communications device function and a second associated with initiating a particular infrastructure-based electronic digital assistant function. When the first, playing back a second audio feedback indicative of acknowledgement of a local device function, and performing the local device function; when the second, playing back, a third audio feedback indicative of acknowledgement of a infrastructure-based electronic digital assistant function, and performing the infrastructure-based electronic digital assistant function.

Abstract: A method for training an endpointer model includes short-form speech utterances and long-form speech utterances. The method also includes providing a short-form speech utterance as input to a shared neural network, the shared neural network configured to learn shared hidden representations suitable for both voice activity detection (VAD) and end-of-query (EOQ) detection. The method also includes generating, using a VAD classifier, a sequence of predicted VAD labels and determining a VAD loss by comparing the sequence of predicted VAD labels to a corresponding sequence of reference VAD labels. The method also includes, generating, using an EOQ classifier, a sequence of predicted EOQ labels and determining an EOQ loss by comparing the sequence of predicted EOQ labels to a corresponding sequence of reference EOQ labels. The method also includes training, using a cross-entropy criterion, the endpointer model based on the VAD loss and the EOQ loss.

Abstract: An enterprise data management system with definition quality assessment capabilities for automatically assessing the quality of definitions for terms stored in the enterprise data management system. The system can include a processor programmed to receive a term and a corresponding definition. The processor assess the quality of the definition, including for each of a plurality of quantifiable definition guidelines: deriving feature inputs based on the definition; feeding the feature inputs into a machine learning model corresponding to the definition guideline; and receiving a quality score for the definition guideline from the corresponding machine learning model. An overall quality score is calculated based on the quality score for each of the definition guidelines. The overall quality score and the quality score for each of the plurality of definition guidelines is displayed and if the overall quality score is less than a selected threshold score, a transformation of the definition is recommended.

Abstract: An electronic device and method are disclosed herein. The electronic device includes a network interface and processor. The processor implements the method, including receiving a voice input through a network interface as transmitted from a first external device, including a request to execute a function using at least one application which is not indicated in the voice input, extracting a first text from the voice input by executing automatic speech recognition (ASR), when the at least one application is identified based on the first text, transmitting, through the network interface to the first external device, second data associated with the identified at least one application for display by the first external device, and when the at least one application is not identified based at least in part on the first text, reattempting identification of the at least one application by executing natural language understanding (NLU) on the first text.

Abstract: Voice activity detection (VAD) is an enabling technology for a variety of speech based applications. Herein disclosed is a robust VAD algorithm that is also language independent. Rather than classifying short segments of the audio as either “speech” or “silence”, the VAD as disclosed herein employees a soft-decision mechanism. The VAD outputs a speech-presence probability, which is based on a variety of characteristics.

Abstract: Systems, methods, and apparatuses are described for determining compliance with a plurality of restrictions associated with one or more devices in an organization. First text indicating restrictions may be received, and second text indicating a current configuration of one or more devices may be received. Both sets of text may be processed by, e.g., removing a portion of the text based on a predetermined list of terms and simplifying the text using a lemmatization algorithm. A first vector and second vector may be generated based on the processed sets of text, and each vector may be weighted based on an inverse frequency of words in their respective text. Each vector may be normalized based on semantic analysis. The two vectors may be compared. Based on the comparison, third text corresponding to a portion of the second vector may be generated and transmitted to a third computing device.

Abstract: In some cases, a verbal harassment detection system may use machine learning models to detect verbal harassment in real-time or near real-time. The system may receive an audio segment comprising a portion of audio captured by a microphone located within a vehicle. Further, the system may convert the audio segment to a text segment. The system may provide at least the text segment to a prediction model associated with verbal harassment detection to obtain a harassment prediction. Further, the system may provide the audio segment to an emotion detector to obtain a detected emotion of a speaking user that made an utterance included in the audio segment. Based at least in part on the harassment prediction and the detected emotion, the system may automatically, and without user intervention, determine whether a user is being harassed.

Abstract: The present document relates to audio coding systems which make use of a harmonic transposition method for high frequency reconstruction (HFR), and to digital effect processors, e.g. so-called exciters, where generation of harmonic distortion adds brightness to the processed signal. In particular, a system configured to generate a high frequency component of a signal from a low frequency component of the signal is described. The system may comprise an analysis filter bank (501) configured to provide a set of analysis subband signals from the low frequency component of the signal; wherein the set of analysis subband signals comprises at least two analysis subband signals; wherein the analysis filter bank (501) has a frequency resolution of ?f.