Abstract: Described are platforms, systems, media, and methods for evaluating, monitoring, and/or treating a subject for brain injury based on machine learning analysis of one or more of brain imaging features, clinical features, demographic features, or speech features.

Abstract: Speech analysis devices and methods for identifying migraine attacks are provided. Migraine sufferers can experience changes in speech patterns both during a migraine attack and in a pre-attack phase (e.g., a time period before the migraine attack can be recognized by the migraine sufferer). Embodiments identify or predict migraine attacks during the pre-attack phase and/or the attack phase (such as early stages of a migraine attack) by comparing speech features from one or more speech samples provided by a user against baseline data. The speech features are indicative and/or predictive of migraine onset, and can be personalized to a user and/or based on normative data.

Abstract: Disclosed herein are systems and methods for evaluating or analyzing cognitive function or impairment using speech analysis. In some implementations the evaluation of cognitive function comprises a predicted future cognitive function or change in cognitive function. In some implementations the cognitive function is evaluated using a panel or speech features such as a metric of semantic relevance, MATTR, and other relevant features.

Abstract: Systems, methods, and apparatuses to restore degraded speech via a modified diffusion model are described. An exemplary system is specially configured to train a diffusion-based vocoder containing an upsampler, based on pairing original speech x and degraded speech mel-spectrum mT samples; train a deep convoluted neural network (CNN) upsampler based on a mean absolute error loss to match the estimated original speech {circumflex over (x)}? outputted by the diffusion-based vocoder by extracting the upsampler, generating a reference conditioner, and generating a weighted altered conditioner cTn?. The system further optimizes speech quality to invert non-linear transformation and estimate lost data by feeding the degraded mel-spectrum mT through the CNN upsampler and feeding the degraded mel-spectrum mT through the diffusion-based vocoder. The system then generates estimated original speech {circumflex over (x)}? based on the corresponding degraded speech mel-spectrum mT. Other related embodiments are described.

Abstract: Described are platforms, systems, media, and methods for maintaining a database of items associated with one or more skill requirements and a visit duration; maintaining a database of experts associated with one or more skill proficiencies, a location, and a schedule; receiving a request from a consumer for delivery by an expert of one or more items in the database to a consumer address; identifying experts in the database having skill proficiencies matching the skill requirements of the one or more items and available in a timeslot for the visit duration of the one or more items; presenting timeslots for which one or more experts are identified to the consumer and allowing the consumer to select a timeslot; and selecting an expert from among the identified experts in the selected timeslot based on shortest travel time; provided that utilization of the selected expert exceeds a predetermined utilization threshold.

Abstract: Disclosed herein are platforms, systems, software, and methods for evaluating social behavior. Speech or audio data can be analyzed to identify elemental language and acoustic components of speech that are used to determine higher order effects such as social behavior. Disclosed herein are models developed to address the assessment of mental health status (e.g. diagnosis and assessment of neurocognition and symptom ratings). In some embodiments, disclosed herein are models configured to predict performance on social and functional competency assessments. The present disclosure demonstrates the ability of a set of language features to provide several relevant upstream and/or downstream clinical assessments on audio derived data such as transcripts that were never seen during model training and showed consistent performance on all tasks of interest.

Abstract: Hierarchical coarse-grain sparsity for deep neural networks is provided. An algorithm-hardware co-optimized memory compression technique is proposed to compress deep neural networks in a hardware-efficient manner, which is referred to herein as hierarchical coarse-grain sparsity (HCGS). HCGS provides a new long short-term memory (LSTM) training technique which enforces hierarchical structured sparsity by randomly dropping static block-wise connections between layers. HCGS maintains the same hierarchical structured sparsity throughout training and inference; this reduces weight storage for both training and inference hardware systems.

Abstract: Disclosed herein are systems, devices, and methods for evaluating or analyzing complex audio signals using multi-dimensional statistical signatures and machine learning algorithms. One advantage of the present disclosure is the ability for remote evaluation of respiratory tract health using speech analysis. The need for remote collection capabilities that can sensitively and reliably characterize respiratory tract function is particularly pertinent in view of the recent Covid-19 pandemic, which may adversely affect the health of individuals who could already be experiencing health problems with respiratory tract function.

Abstract: Systems, devices, and methods for tracking articulatory and prosodic development in children are disclosed. Human speech in a given language can be divided into phonemes, which are a sound or group of sounds perceived by speakers of the language to have a common linguistic function (e.g., consonant sounds, vowel sounds). In an exemplary aspect, a normative model can be generated for production characteristics of each phoneme in a given language using a database of normative speech samples. One or more speech samples of a human subject can be analyzed to identify the phonemes used by the human subject and measured against the normative model. Based on this analysis, a normed score is generated of the articulation accuracy, duration, rhythm, volume, and/or other production characteristics for each phoneme of the speech sample of the human subject.

Abstract: Systems, methods, and apparatuses to restore degraded speech via a modified diffusion model are described. An exemplary system is specially configured to train a diffusion-based vocoder containing an upsampler, based on pairing original speech x and degraded speech mel-spectrum mT samples; train a deep convoluted neural network (CNN) upsampler based on a mean absolute error loss to match the estimated original speech {circumflex over (x)}? outputted by the diffusion-based vocoder by extracting the upsampler, generating a reference conditioner, and generating a weighted altered conditioner ??Tn. The system further optimizes speech quality to invert non-linear transformation and estimate lost data by feeding the degraded mel-spectrum mT through the CNN upsampler and feeding the degraded mel-spectrum mT through the diffusion-based vocoder. The system then generates estimated original speech {circumflex over (x)}? based on the corresponding degraded speech mel-spectrum mT. Other related embodiments are described.

Abstract: Systems and methods for objective assessment of patient response for calibration of therapeutic interventions are pro-vided. Analysis of a human patient's speech provides an objective measurement for pain or discomfort experienced by a patient. This speech analysis can then be used to provide personalized therapeutic interventions which more effectively address the needs of the patient. The speech analysis provides not only a personalized initial intervention, but in the case of ongoing interventions the speech analysis can further refine the intervention as a patient's response changes over time.

Abstract: Speech analysis devices and methods for identifying migraine attacks are provided. Migraine sufferers can experience changes in speech patterns both during a migraine attack and in a pre-attack phase (e.g., a time period before the migraine attack can be recognized by the migraine sufferer). Embodiments identify or predict migraine attacks during the pre-attack phase and/or the attack phase (such as early stages of a migraine attack) by comparing speech features from one or more speech samples provided by a user against baseline data. The speech features are indicative and/or predictive of migraine onset, and can be personalized to a user and/or based on normative data.

Abstract: Various embodiments of a systems and methods for a triplet network having speaker diarization are disclosed.

Abstract: Systems and methods use patient speech samples as inputs, use subjective multi-point ratings by speech-language pathologists of multiple perceptual dimensions of patient speech samples as further inputs, and extract laboratory-implemented features from the patient speech samples. A predictive software model learns the relationship between speech acoustics and the subjective ratings of such speech obtained from speech-language pathologists, and is configured to apply this information to evaluate new speech samples. Outputs may include objective evaluation of the plurality of perceptual dimensions for new speech samples and/or evaluation of disease onset, disease progression, or disease treatment efficacy for a condition involving dysarthria as a symptom, utilizing the new speech samples.

Abstract: Systems and methods use patient speech samples as inputs, use subjective multi-point ratings by speech-language pathologists of multiple perceptual dimensions of patient speech samples as further inputs, and extract laboratory-implemented features from the patient speech samples. A predictive software model learns the relationship between speech acoustics and the subjective ratings of such speech obtained from speech-language pathologists, and is configured to apply this information to evaluate new speech samples. Outputs may include objective evaluation of the plurality of perceptual dimensions for new speech samples and/or evaluation of disease onset, disease progression, or disease treatment efficacy for a condition involving dysarthria as a symptom, utilizing the new speech samples.

Abstract: Various embodiments of a systems and methods for a triplet network having speaker diarization are disclosed.

Abstract: Disclosed herein are speech therapeutic devices and methods. In one aspect, the speech therapeutic device includes audio input circuitry, signal processing circuitry, and stimulus circuitry. In certain embodiments, the audio input circuitry is configured to provide an input signal that is indicative of speech provided by a user and the signal processing circuitry is configured to utilize a reconfigurable rule that includes a condition, receive the input signal, process the input signal using the reconfigurable rule, and provide an alert signal responsive to attainment of the condition. The stimulus circuitry is configured to receive the alert signal and provide a stimulus to the user. The signal processing circuitry is additionally configured to (i) receive the reconfigurable rule from a communication network, and/or (ii) generate a record indicative of the alert signal, store the record in a memory, and send the record to a communication network.

Abstract: Disclosed herein are speech therapeutic devices and methods. In one aspect, the speech therapeutic device includes audio input circuitry, signal processing circuitry, and stimulus circuitry. In certain embodiments, the audio input circuitry is configured to provide an input signal that is indicative of speech provided by a user and the signal processing circuitry is configured to utilize a reconfigurable rule that includes a condition, receive the input signal, process the input signal using the reconfigurable rule, and provide an alert signal responsive to attainment of the condition. The stimulus circuitry is configured to receive the alert signal and provide a stimulus to the user. The signal processing circuitry is additionally configured to (i) receive the reconfigurable rule from a communication network, and/or (ii) generate a record indicative of the alert signal, store the record in a memory, and send the record to a communication network.

Abstract: Disclosed herein are speech therapeutic devices and methods. In one aspect, the speech therapeutic device includes audio input circuitry, signal processing circuitry, and stimulus circuitry. In certain embodiments, the audio input circuitry is configured to provide an input signal that is indicative of speech provided by a user and the signal processing circuitry is configured to utilize a reconfigurable rule that includes a condition, receive the input signal, process the input signal using the reconfigurable rule, and provide an alert signal responsive to attainment of the condition. The stimulus circuitry is configured to receive the alert signal and provide a stimulus to the user. The signal processing circuitry is additionally configured to (i) receive the reconfigurable rule from a communication network, and/or (ii) generate a record indicative of the alert signal, store the record in a memory, and send the record to a communication network.

Abstract: Disclosed herein are speech therapeutic devices and methods. In one aspect, the speech therapeutic device includes audio input circuitry, signal processing circuitry, and stimulus circuitry. In certain embodiments, the audio input circuitry is configured to provide an input signal that is indicative of speech provided by a user and the signal processing circuitry is configured to utilize a reconfigurable rule that includes a condition, receive the input signal, process the input signal using the reconfigurable rule, and provide an alert signal responsive to attainment of the condition. The stimulus circuitry is configured to receive the alert signal and provide a stimulus to the user. The signal processing circuitry is additionally configured to (i) receive the reconfigurable rule from a communication network, and/or (ii) generate a record indicative of the alert signal, store the record in a memory, and send the record to a communication network.