Abstract: An electronic device displays a messaging interface that allows a participant in a message conversation to capture, send, and/or play media content. The media content includes images, video, and/or audio. The media content is captured, sent, and/or played based on the electronic device detecting one or more conditions.

Abstract: Techniques for the generation of dubbed audio for an audio/video are described.

Abstract: Post-filtering may be performed for ratio masks as part of audio enhancement. Audio data may be received. A machine learning model may be applied to generate gain values for different spectrum bands of the audio data. The gain values may then be modified using an envelope post-filter according to a monotonically increasing function applied to the gain values to produce modified gain values used to generate an enhanced version of the audio data.

Abstract: An electronic device includes a touch-sensitive surface, a display, and a camera sensor. The device displays a message region for displaying a message conversation and receives a request to add media to the message conversation. Responsive to receiving the request, the device displays a media selection interface concurrently with at least a portion of the message conversation. The media selection interface includes a plurality of affordances for selecting media for addition to the message conversation, the plurality of affordances includes a live preview affordance, at least a subset of the plurality of affordances includes thumbnail representations of media available for adding to the message conversation, and the live preview affordance is associated with a live camera preview. Responsive to detecting selection of the live preview affordance, the device captures a new image based on the live camera preview and selects the new image for addition to the message conversation.

Abstract: Systems, methods, and apparatuses for providing a device health service are described. In some examples, a method includes receiving a request to perform a model transfer to generate a model to use on previously unseen data; receiving previously unseen data; determining a previously seen feature data most closely resembles the received previously unseen data; mapping, using the determined previously seen feature, the previously unseen data to labels; training a model using the mapped labels and the previously unseen data; and performing inference using the trained model.

Abstract: Systems, methods, and apparatuses for detecting anomalies using clusters are described. In some examples, a method includes receiving a request to perform anomaly detection using a plurality of clusters; receiving a data point; determining when the received data point is a part of one of the plurality of clusters utilizing a distance to centers of the one or more clusters, wherein: when the received data point is determined to belong to a normal cluster, assigning the received data point to the determined cluster, updating the cluster, and updating a history for the cluster, when the received data point is determined to belong to an anomalous cluster, raising an anomaly, updating the cluster, and updating a history for the cluster, and when the received data point is determined to not belong to any cluster, raising an anomaly.

Abstract: Systems, methods, and apparatuses for selecting a model are described. In some examples, a method of selecting a model includes receiving a request to perform model selection; evaluating a plurality of models to select model by: generating a plurality of metrics for each of the trained plurality of models, the plurality of metrics including at least two of an forewarning time metric of how much in advance of a failure an alert can be raised by the model, event recall metric of how many failure events were alerted to in advance of failure, an event precision metric of a ratio of true and false positives, and an area under a receiver operating characteristic (ROC) curve, calculating, for each of the trained plurality of models, a weighted harmonic mean from the at least two metrics, and selecting one of plurality of models based on the calculated weighted harmonic means; and generating and providing a report regarding the selected trained model.

Abstract: Systems, methods, and apparatuses for providing an estimation of remaining useful life are described. In some examples, a method for providing an estimation of remaining useful life includes receiving a request to determine a remaining useful life of a managed device before maintenance using a trained machine learning model; receiving sensor data from the managed device; applying the trained machine learning model to the received information to generate a prediction of a time to failure of the managed device and a confidence interval for that prediction; and providing the prediction of a time to failure and confidence interval for that prediction to a requester.

Abstract: An electronic device includes a touch-sensitive surface, a display, and a camera sensor. The device displays a message region for displaying a message conversation and receives a request to add media to the message conversation. Responsive to receiving the request, the device displays a media selection interface concurrently with at least a portion of the message conversation. The media selection interface includes a plurality of affordances for selecting media for addition to the message conversation, the plurality of affordances includes a live preview affordance, at least a subset of the plurality of affordances includes thumbnail representations of media available for adding to the message conversation, and the live preview affordance is associated with a live camera preview. Responsive to detecting selection of the live preview affordance, the device captures a new image based on the live camera preview and selects the new image for addition to the message conversation.

Abstract: A speech recognition system for resolving impaired utterances can have a speech recognition engine configured to receive a plurality of representations of an utterance and concurrently to determine a plurality of highest-likelihood transcription candidates corresponding to each respective representation of the utterance. The recognition system can also have a selector configured to determine a most-likely accurate transcription from among the transcription candidates. As but one example, the plurality of representations of the utterance can be acquired by a microphone array, and beamforming techniques can generate independent streams of the utterance across various look directions using output from the microphone array.

Abstract: Method for echo control using adaptive polynomial filters in sub-band domain starts with loudspeaker that is configured to be driven by a reference signal outputting a loudspeaker signal. Microphone receives at least one of: a near-end speaker signal, ambient noise signal, or the loudspeaker signal and generates a microphone signal. Adaptive polynomial filters in sub-band domain included in adaptive echo canceller (AEC) are configured to adaptively filter representation of the reference signal in a plurality of channels in a sub-band domain based on a clean signal to generate the echo estimate. Echo suppressor is configured to remove an echo estimate from the microphone signal to generate the clean signal. Other embodiments are described.

Abstract: A speech recognition system for resolving impaired utterances can have a speech recognition engine configured to receive a plurality of representations of an utterance and concurrently to determine a plurality of highest-likelihood transcription candidates corresponding to each respective representation of the utterance. The recognition system can also have a selector configured to determine a most-likely accurate transcription from among the transcription candidates. As but one example, the plurality of representations of the utterance can be acquired by a microphone array, and beamforming techniques can generate independent streams of the utterance across various look directions using output from the microphone array.

Abstract: A speech recognition system for resolving impaired utterances can have a speech recognition engine configured to receive a plurality of representations of an utterance and concurrently to determine a plurality of highest-likelihood transcription candidates corresponding to each respective representation of the utterance. The recognition system can also have a selector configured to determine a most-likely accurate transcription from among the transcription candidates. As but one example, the plurality of representations of the utterance can be acquired by a microphone array, and beamforming techniques can generate independent streams of the utterance across various look directions using output from the microphone array.

Abstract: A speech recognition system for resolving impaired utterances can have a speech recognition engine configured to receive a plurality of representations of an utterance and concurrently to determine a plurality of highest-likelihood transcription candidates corresponding to each respective representation of the utterance. The recognition system can also have a selector configured to determine a most-likely accurate transcription from among the transcription candidates. As but one example, the plurality of representations of the utterance can be acquired by a microphone array, and beamforming techniques can generate independent streams of the utterance across various look directions using output from the microphone array.

Abstract: A speech recognition system for resolving impaired utterances can have a speech recognition engine configured to receive a plurality of representations of an utterance and concurrently to determine a plurality of highest-likelihood transcription candidates corresponding to each respective representation of the utterance. The recognition system can also have a selector configured to determine a most-likely accurate transcription from among the transcription candidates. As but one example, the plurality of representations of the utterance can be acquired by a microphone array, and beamforming techniques can generate independent streams of the utterance across various look directions using output from the microphone array.

Abstract: Automatic gain control systems disclosed herein can incorporate a confidence metric that can estimate the accuracy of gain adjustments calculated by an automatic gain control module. The confidence metric may be based on a percentage of valid audio samples in a given period of time. Based on the confidence metric, the AGC response may be reduced, delayed, frozen, or otherwise altered from the baseline gain adjustment. Time-averaging process may be used to estimate the input signal power level and determine an appropriate baseline gain adjustment. Additionally, weighting functions can be adjusted to prevent overestimation of the signal power.

Abstract: A speech recognition system for resolving impaired utterances can have a speech recognition engine configured to receive a plurality of representations of an utterance and concurrently to determine a plurality of highest-likelihood transcription candidates corresponding to each respective representation of the utterance. The recognition system can also have a selector configured to determine a most-likely accurate transcription from among the transcription candidates. As but one example, the plurality of representations of the utterance can be acquired by a microphone array, and beamforming techniques can generate independent streams of the utterance across various look directions using output from the microphone array.

Abstract: Apparatus for linear and nonlinear acoustic echo control includes loudspeaker, first, second, and third microphone, beamformer, and first echo canceller. The loudspeaker outputs a loudspeaker signal that includes reference signal. The first microphone and the second microphone are collocated with the loudspeaker, receive at least one of: a near-end speaker signal from a near-end speaker and the loudspeaker signal, and generate first and second microphone uplink signals, respectively. The third microphone receives the near-end speaker signal and generates a third microphone uplink signal. The beamformer receives the first and second microphone uplink signals, directs a beam towards the loudspeaker and drives a null towards the near-end speaker, and generates a beamformer output. The first echo canceler receives the third microphone uplink signal and the beamformer output, and cancels echoes in the third microphone uplink signal based on the beamformer output to generate an echo cancelled signal.

Abstract: Systems and methods for speech recognition system having a speech processor that is trained to recognize speech by considering (1) a raw microphone signal that includes an echo signal and (2) different types of echo information signals from an echo cancellation system (and optionally different types of ambient noise suppression signals from a noise suppressor). The different types of echo information signals may include those used for echo cancelation and those having echo information. The speech recognition system may convert the raw microphone signal and different types of echo information signals (and optional noise suppression signals) into spectral features in the form of a vector, and a concatenator to combine the feature vectors into a total vector (for a period of time) that is used to train the speech processor, and during use of the speech processor to recognize speech.

Abstract: Method of improving audio signal in the spectral domain starts by receiving audio signal that includes signals from sources including speech source and music source. Audio signal is tuned for output by sound output device. Portions of audio signal are analyzed in a spectral domain to determine whether adjustments are required. Analyzing portions of audio signal includes determining whether anomaly is present in frequency band of audio signal in spectral domain by using at least one metric. Metrics include band energy ratios, spectral centroid, spectral tilt, spectral flux, spectral variance, absolute thresholds, and relative thresholds. Audio signal is adjusted to improve audio signal in spectral domain when audio signal is determined to require adjustments. Adjusting audio signal includes adjusting values of the metric in frequency band that is determined to include anomaly to correspond to clustering of metric values for audio signal in spectral domain. Other embodiments are also described.