An adaptive music playback system is disclosed. The system includes a composition system that receives information corresponding to user activity levels. The composition system determines target musical criteria corresponding to the user activity levels and modifies the composition of a song in response to changes in user activity.

A system is described that permits identified musical phrases or themes to be synchronized and linked into changing real-world events. The achieved synchronization includes a seamless musical transitionachieved using a timing offset, such as relative advancement of an significant musical onset, that is inserted to align with a pre-existing but identified music signature, beat or timebasebetween potentially disparate pre-identified musical phrases having different emotive themes defined by their respective time signatures, intensities, keys, musical rhythms and/or musical phrasing. The system operates to augment an overall sensory experience of a user in the real world by dynamically changing, re-ordering or repeating and then playing audio themes within the context of what is occurring in the surrounding physical environment, e.g. during different phases of a cardio workout in a step class the music rate and intensity increase during sprint periods and decrease during recovery periods.

A media-content augmentation system includes a processing system that receives input data in the form of temporally-varying events data. The processing system resolves the input into one or more categorized contextual themes, correlates the themes with metadata associated with at least one reference media file, and then splices or fades together selected parts of the media file, thus generating as an output, a media product in which transitions between its contextual themes are aligned with selected temporal events in the input data. The temporarily-varying events take the form of a beginning and an end in the case of a sustained feature, or a specific point in time for a hit point. A method aligns sections in digital media files with temporally-varying events data to compose a media product. The system augments a sensory experience of a user by dynamically changing and then playing selected media files within the context of the categorized themes input to the processing system.

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.

An apparatus is provided that accurately estimates a point at which a musical performance is started by a player. The apparatus includes the musical performance analysis unit 32, and the musical performance analysis unit 32 obtains action data that includes a time series of feature data representing actions made by a player during a musical performance for a reference period and estimating a sound-production point based on the action data at an estimated point using a learned model L.

Disclosed are a system and a method for singing expression transplantation. A singing expression transplantation method performed by a singing expression transplantation system according to an embodiment may comprise the steps of: synchronizing each of a first sound source and a second sound source, which include different pieces of voice information with regard to an identical song; modifying the pitch of the first sound source on the basis of pitch information extracted from each of the first sound source and the second sound source, which have been synchronized; and extracting volume information from each of the first sound source and the second sound source and adjusting the magnitude of the volume regarding the first sound source, the pitch of which has been modified, according to each piece of extracted volume information.

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.

In general, the subject matter described in this disclosure can be embodied in methods, systems, and program products. A computing device stores reference song characterization data and receives digital audio data. The computing device determines whether the digital audio data represents music and then performs a different process to recognize that the digital audio data represents a particular reference song. The computing device then outputs an indication of the particular reference song.

A lyrics analyzer generates tags and explicitness indicators for a set of tracks. These tags may indicate the genre, mood, occasion, or other features of each track. The lyrics analyzer does so by generating an n-dimensional vector relating to a set of topics extracted from the lyrics and then using those vectors to train a classifier to determine whether each tag applies to each track. The lyrics analyzer may also generate playlists for a user based on a single seed song by comparing the lyrics vector or the lyrics and acoustics vectors of the seed song to other songs to select songs that closely match the seed song. Such a playlist generator may also take into account the tags generated for each track.

Systems and methods are provided for using a common vocabulary, predefined or dynamically generated based on user-provided content, to transform biometric and/or neurometric data collected from one or more people into a coherent audio and/or visual result. One method comprises receiving a first incoming signal from a bio-generated data sensing device worn by a first user; determining a first set of output values based on the first incoming signal, a common vocabulary comprising a list of possible output values, and a parameter file comprising a set of instructions for applying the common vocabulary to the first incoming signal to derive the first set of output values; generating a first output array comprising the first set of output values; and providing the first output array to an output delivery system configured to render the first output array as a first audio and/or visual output.