Abstract: The subject technology provides a framework for estimating respiratory rates from audio data recordings. A multi-task learning network may be trained to output respiratory rates, breathing conditions, and/or noise conditions based on input audio data recordings. The audio data recordings may be generated using wearable audio devices with near-field microphones. The respiratory rates may be provided along with other workout information by a health application of an electronic device. Additional sensor data and/or health data may be used in combination with the audio data and/or the respiratory rates and/or breathing conditions for respiratory and/or other health monitoring by an electronic device.

Abstract: The subject technology provides physiological state prediction based on acoustic data using machine learning. An apparatus receives input data comprising acoustic signal information associated with a user. The apparatus extracts one or more acoustic features from the acoustic signal information. The apparatus produces a trained machine learning model by training a neural network to predict one or more physiological states of the user from the one or more acoustic features.

Abstract: A system can receive an input indicating a user condition. The system can also receive an internal audio stream from an in-ear microphone and an external audio stream from an external microphone of a head worn system. The system can determine a respiration rate of a user based on the internal audio stream, the external audio stream, and the input indicating the user condition. In some implementations, the respiration rate may be determined from a respiration signal in the internal audio stream and/or the external audio stream. The respiration signal may measure breathing of the user. In some implementations, the system can invoke a machine learning model to determine the respiration signal from the internal audio stream and/or the external audio stream based on the user condition.

Abstract: Systems and methods for speech recognition are provided. In some aspects, the method comprises receiving, using an input, an audio signal. The method further comprises splitting the audio signal into auditory test segments. The method further comprises extracting, from each of the auditory test segments, a set of acoustic features. The method further comprises applying the set of acoustic features to a deep neural network to produce a hypothesis for the corresponding auditory test segment. The method further comprises selectively performing one or more of: indirect adaptation of the deep neural network and direct adaptation of the deep neural network.

Abstract: A computing system determines whether a reference audio signal contains a query. A time-frequency convolutional neural network (TFCNN) comprises a time and frequency convolutional layers and a series of additional layers, which include a bottleneck layer. The computation engine applies the TFCNN to samples of a query utterance at least through the bottleneck layer. A query feature vector comprises output values of the bottleneck layer generated when the computation engine applies the TFCNN to the samples of the query utterance. The computation engine also applies the TFCNN to samples of the reference audio signal at least through the bottleneck layer. A reference feature vector comprises output values of the bottleneck layer generated when the computation engine applies the TFCNN to the samples of the reference audio signal. The computation engine determines at least one detection score based on the query feature vector and the reference feature vector.

Abstract: Systems and methods for speech recognition are provided. In some aspects, the method comprises receiving, using an input, an audio signal. The method further comprises splitting the audio signal into auditory test segments. The method further comprises extracting, from each of the auditory test segments, a set of acoustic features. The method further comprises applying the set of acoustic features to a deep neural network to produce a hypothesis for the corresponding auditory test segment. The method further comprises selectively performing one or more of: indirect adaptation of the deep neural network and direct adaptation of the deep neural network.

Abstract: A computing system determines whether a reference audio signal contains a query. A time-frequency convolutional neural network (TFCNN) comprises a time and frequency convolutional layers and a series of additional layers, which include a bottleneck layer. The computation engine applies the TFCNN to samples of a query utterance at least through the bottleneck layer. A query feature vector comprises output values of the bottleneck layer generated when the computation engine applies the TFCNN to the samples of the query utterance. The computation engine also applies the TFCNN to samples of the reference audio signal at least through the bottleneck layer. A reference feature vector comprises output values of the bottleneck layer generated when the computation engine applies the TFCNN to the samples of the reference audio signal. The computation engine determines at least one detection score based on the query feature vector and the reference feature vector.

Abstract: A computer-implemented method can include a speech collection module collecting a speech pattern from a patient, a speech feature computation module computing at least one speech feature from the collected speech pattern, a mental health determination module determining a state-of-mind of the patient based at least in part on the at least one computed speech feature, and an output module providing an indication of a diagnosis with regard to a possibility that the patient is suffering from a certain condition such as depression or Post-Traumatic Stress Disorder (PTSD).

Abstract: A computer-implemented method can include a speech collection module collecting a speech pattern from a patient, a speech feature computation module computing at least one speech feature from the collected speech pattern, a mental health determination module determining a state-of-mind of the patient based at least in part on the at least one computed speech feature, and an output module providing an indication of a diagnosis with regard to a possibility that the patient is suffering from a certain condition such as depression or Post-Traumatic Stress Disorder (PTSD).