The disclosed computer-implemented method may include accessing an audio stream with heterogenous audio content; dividing the audio stream into a plurality of frames; generating a plurality of spectrogram patches, each spectrogram patch within the plurality of spectrogram patches being derived from a frame within the plurality of frames; and providing each spectrogram patch within the plurality of spectrogram patches as input to a convolutional neural network classifier and receiving, as output, a classification of music within a corresponding frame from within the plurality of frames. Various other methods, systems, and computer-readable media are also disclosed.

A vehicle engine sound control system identifies a vehicle driver by a driver smartphone or a driver biometric information detecting sensor and analyzes the music to which the identified driver listens with the driver smartphone or a vehicle infotainment system. A traveling pattern of the driver is analyze by applying any one among a vehicle, a GPS, a road, and weather as a condition. A driver propensity engine sound pattern is generated as a result value by learning at least any one information among a driver identifying unit, a music analyzing unit, and a travel analyzing unit. The engine sound is adjusted and output based the result value.

A method implemented by a determination engine is provided. The determination engine receives a media dataset comprising target piece music information, target piece audience information, corpus music information, corpus audience information, and corpus preference data. The determination engine determines a subset of the corpus music and preference information and determines at least one surprise factor of the subset of the corpus music and preference information across features at one of a plurality of orders. The determination engine learns a model that estimates a likelihood that time-varying surprise trends across the features achieves a preference level. The determination engine determines at least one surprise factor of the target piece music information across the features at the one of the plurality of orders and predicts, using the model, preference information using the time-varying surprise trends for the target piece music information across the features.

The system recommends a media content item, from among a plurality of media content items, for performance by a user. The performance can include a series of actions, which can optionally be recorded or otherwise captured to be considered as collaborative content. The system analyzes at least one physical performance property relative to a corresponding physical performance property of each of the plurality of media content items. The at least one physical performance property is determined from profile information that is associated with the user, and may include a temporal, spectral, video, audio, or other property. Based on the analysis, the system identifies the media content item as being compatible or incompatible for performance or collaboration by the user. The system generates for output, which can include storage in memory or display on a device, a recommendation of the media content item on a device.

The system generates a recommendation for collaborative content to be consumed, thus allowing a large field of content to be parsed. The content may include audio content, video content, image content, or other content. The system identifies a collaborative content and a base content upon which the collaborative content is generated. Based on analysis of the collaborative content and profile information, the system determines recommendation metric, or a score. Based on the metric, the system generates a recommendation of the collaborative content. Collaborative content that is better formed based on signal properties, favorably compared to the base content, created by more highly rated users, or formatted in a preferred way may be more strongly recommended. Signal properties include temporal, spectral, audio, or visual properties of the content. The system outputs the recommendation for storage, display, or both to provide guidance to users consuming or reviewing collaborative content.

A deep learning method-based tonal balancing method, apparatus, and system, the method includes: extracting features from audio data to obtain audio data features, generating audio balancing results by using a trained audio balancing model based on the obtained audio data features. The present invention employs deep neural networks and unsupervised deep learning method to solve the problems of audio balancing of unlabeled music and music of unknown style. The present invention also combines user preferences statistics to achieve a more rational multi-style audio balancing design to meet individual needs.

An intelligent system for matching audio with video of the present invention provides a video analysis module targeting color tone, storyboard pace, video dialogue, length and category and director's special requirement, actors expression, movement, weather, scene, buildings, spacial and temporal, things and a music analysis module targeting recorded music form, sectional turn, style, melody and emotional tension, and then uses an AI matching module to adequately match video of the video analysis module with musical characteristics of the music analysis module, so as to quickly complete a creative composition selection function with respect to matching audio with a video.

A method for automatically generating an audio signal, the method comprising receiving a source audio signal analyzing the source audio signal to identify a musical parameter characteristic thereof obtaining a supplemental audio signal based on the identified musical parameter characteristic and combining the source audio signal and the supplemental audio signal to form an extended audio signal.

Implementations generally relate to automated equalizer adjustments based on audio characteristics. In some implementations, a method includes detecting music that is being currently played on an audio device. The method further includes adjusting one or more equalizer settings of an equalizer device based at least in part on a music genre associated with the music. The method further includes outputting the music based at least in part on the adjusting of the one or more equalizer settings of the equalizer device.

A computer receives a first audio content item and applies a process to generate a representation of first audio content item. A portion is extracted from the representation of the first audio content item. A first representative vector that corresponds to the first audio content item is determined by applying a variational autoencoder (VAE) to a first segment of the extracted portion the audio content item. The computer stores the first representative vector that corresponds to the first audio content item.