According to an aspect, a method for distributed sound/image recognition using a wearable device includes receiving, via at least one sensor device, sensor data, and detecting, by a classifier of the wearable device, whether or not the sensor data includes an object of interest. The classifier configured to execute a first machine learning (ML) model. The method includes transmitting, via a wireless connection, the sensor data to a computing device in response to the object of interest being detected within the sensor data, where the sensor data is configured to be used by a second ML model on the computing device or a server computer for further sound/image classification.

According to an aspect, a method for distributed sound/image recognition using a wearable device includes receiving, via at least one sensor device, sensor data, and detecting, by a classifier of the wearable device, whether or not the sensor data includes an object of interest. The classifier configured to execute a first machine learning (ML) model. The method includes transmitting, via a wireless connection, the sensor data to a computing device in response to the object of interest being detected within the sensor data, where the sensor data is configured to be used by a second ML model on the computing device or a server computer for further sound/image classification.

What is described is an apparatus for post-processing an audio signal, having: a time-spectrum-converter for converting the audio signal into a spectral representation having a sequence of spectral frames; a prediction analyzer for calculating prediction filter data for a prediction over frequency within a spectral frame; a shaping filter controlled by the prediction filter data for shaping the spectral frame to enhance a transient portion within the spectral frame; and a spectrum-time-converter for converting a sequence of spectral frames having a shaped spectral frame into a time domain.

A processing load at a receiving side is reduced in a case where a plurality of classes of audio data is transmitted. A predetermined number of audio streams including coded data of a plurality of groups is generated and a container of a predetermined format having this predetermined number of audio streams is transmitted. Command information for creating a command specifying a group to be decoded from among the plurality of groups is inserted into the container and/or the audio stream. For example, a command insertion area for the receiving side to insert a command for specifying a group to be decoded is provided in at least one audio stream among the predetermined number of audio streams.

Provided is an encoding apparatus for integrally encoding and decoding a speech signal and a audio signal, and may include: an input signal analyzer to analyze a characteristic of an input signal; a stereo encoder to down mix the input signal to a mono signal when the input signal is a stereo signal, and to extract stereo sound image information; a frequency band expander to expand a frequency band of the input signal; a sampling rate converter to convert a sampling rate; a speech signal encoder to encode the input signal using a speech encoding module when the input signal is a speech characteristics signal; a audio signal encoder to encode the input signal using a audio encoding module when the input signal is a audio characteristic signal; and a bitstream generator to generate a bitstream.

An illustrative frequency-domain encoder system transforms time-domain data representative of a content instance into frequency-domain data representative of the content instance. The frequency-domain data includes a plurality of complex coefficients each representing different frequency components of a plurality of frequency components incorporated by the content instance. The frequency-domain encoder system generates a frequency-domain data container that includes the complex coefficients of the frequency-domain data and metadata descriptive of the frequency-domain data. Additionally, within the frequency-domain data container, the frequency-domain encoder system integrates the complex coefficients of the frequency-domain data with timing data representative of a time-dependent feature of the content instance. Corresponding systems and methods are also disclosed.

An audio encoder for providing an output signal using an input audio signal includes a patch generator, a comparator and an output interface. The patch generator generates at least one bandwidth extension high-frequency signal, wherein a bandwidth extension high-frequency signal includes a high-frequency band. The high-frequency band of the bandwidth extension high-frequency signal is based on a low frequency band of the input audio signal. A comparator calculates a plurality of comparison parameters. A comparison parameter is calculated based on a comparison of the input audio signal and a generated bandwidth extension high-frequency signal. Each comparison parameter of the plurality of comparison parameters is calculated based on a different offset frequency between the input audio signal and a generated bandwidth extension high-frequency signal. Further, the comparator determines a comparison parameter from the plurality of comparison parameters, wherein the determined comparison parameter fulfils a predefined criterion.

An audio encoder for providing an output signal using an input audio signal includes a patch generator, a comparator and an output interface. The patch generator generates at least one bandwidth extension high-frequency signal, wherein a bandwidth extension high-frequency signal includes a high-frequency band. The high-frequency band of the bandwidth extension high-frequency signal is based on a low frequency band of the input audio signal. A comparator calculates a plurality of comparison parameters. A comparison parameter is calculated based on a comparison of the input audio signal and a generated bandwidth extension high-frequency signal. Each comparison parameter of the plurality of comparison parameters is calculated based on a different offset frequency between the input audio signal and a generated bandwidth extension high-frequency signal. Further, the comparator determines a comparison parameter from the plurality of comparison parameters, wherein the determined comparison parameter fulfils a predefined criterion.

A method includes receiving training data that includes unspoken text utterances, un-transcribed non-synthetic speech utterances, and transcribed non-synthetic speech utterances. Each unspoken text utterance is not paired with any corresponding spoken utterance of non-synthetic speech. Each un-transcribed non-synthetic speech utterance is not paired with a corresponding transcription. Each transcribed non-synthetic speech utterance is paired with a corresponding transcription. The method also includes generating a corresponding synthetic speech representation for each unspoken textual utterance of the received training data using a text-to-speech model. The method also includes pre-training an audio encoder on the synthetic speech representations generated for the unspoken textual utterances, the un-transcribed non-synthetic speech utterances, and the transcribed non-synthetic speech utterances to teach the audio encoder to jointly learn shared speech and text representations.

A method includes receiving training data that includes unspoken text utterances, un-transcribed non-synthetic speech utterances, and transcribed non-synthetic speech utterances. Each unspoken text utterance is not paired with any corresponding spoken utterance of non-synthetic speech. Each un-transcribed non-synthetic speech utterance is not paired with a corresponding transcription. Each transcribed non-synthetic speech utterance is paired with a corresponding transcription. The method also includes generating a corresponding synthetic speech representation for each unspoken textual utterance of the received training data using a text-to-speech model. The method also includes pre-training an audio encoder on the synthetic speech representations generated for the unspoken textual utterances, the un-transcribed non-synthetic speech utterances, and the transcribed non-synthetic speech utterances to teach the audio encoder to jointly learn shared speech and text representations.