Abstract: Techniques are disclosed relating to implementing audio techniques for real-time audio generation. For example, a music generator system may generate new music content from playback music content based on different parameter representations of an audio signal. In some cases, an audio signal can be represented by both a graph of the signal (e.g., an audio signal graph) relative to time and a graph of the signal relative to beats (e.g., a signal graph). The signal graph is invariant to tempo, which allows for tempo invariant modification of audio parameters of the music content in addition to tempo variant modifications based on the audio signal graph.

Abstract: Disclosed techniques relate to user control of generative music. In some embodiments, a computing system generates a musical plan based on both conversational inputs (e.g., using a large-language model (LLM)) and non-conversational inputs (e.g., via a traditional user interface) to a hybrid interface. The computing system may generate an initial version of the musical plan based on the LLM context and update the context and plan based on various types of user input via the hybrid interface. Disclosed techniques may advantageously allow guided user control over generative music systems.

Abstract: Techniques are disclosed relating to implementing audio techniques for real-time audio generation. For example, a music generator system may generate new music content from playback music content based on different parameter representations of an audio signal. In some cases, an audio signal can be represented by both a graph of the signal (e.g., an audio signal graph) relative to time and a graph of the signal relative to beats (e.g., a signal graph). The signal graph is invariant to tempo, which allows for tempo invariant modification of audio parameters of the music content in addition to tempo variant modifications based on the audio signal graph.

Abstract: Disclosed techniques relate to user control of generative music. In some embodiments, a computing system generates a musical plan based on both conversational inputs (e.g., using a large-language model (LLM)) and non-conversational inputs (e.g., via a traditional user interface) to a hybrid interface. The computing system may generate an initial version of the musical plan based on the LLM context and update the context and plan based on various types of user input via the hybrid interface. Disclosed techniques may advantageously allow guided user control over generative music systems.

Abstract: Techniques are disclosed relating to automatically generating new music content based on image representations of audio files. A music generation system includes a music generation subsystem and a music classification subsystem. The music generation subsystem may generate output music content according to music parameters that define policy for generating music. The classification subsystem may be used to classify whether music is generated by the music generation subsystem or is professionally produced music content. The music generation subsystem may implement an algorithm that is reinforced by prediction output from the music classification subsystem. Reinforcement may include tuning the music parameters to generate more human-like music content.

Abstract: Disclosed techniques relate to user control of generative music. In some embodiments, a computing system generates a musical plan based on both conversational inputs (e.g., using a large-language model (LLM)) and non-conversational inputs (e.g., via a traditional user interface) to a hybrid interface. The computing system may generate an initial version of the musical plan based on the LLM context and update the context and plan based on various types of user input via the hybrid interface. Disclosed techniques may advantageously allow guided user control over generative music systems.

Abstract: Techniques are disclosed relating to implementing audio techniques for real-time audio generation. For example, a music generator system may generate new music content from playback music content based on different parameter representations of an audio signal. In some cases, an audio signal can be represented by both a graph of the signal (e.g., an audio signal graph) relative to time and a graph of the signal relative to beats (e.g., a signal graph). The signal graph is invariant to tempo, which allows for tempo invariant modification of audio parameters of the music content in addition to tempo variant modifications based on the audio signal graph.

Abstract: Techniques are disclosed relating to automatically generate new music content. In some embodiments, a computing system receivers user input specifying a user-defined music control element. The computing system may train a machine learning model to change both composition and performance parameters based on user adjustments to the user-defined music control element. In embodiments in which composition and performance subsystems are on different devices, one device may transmit configuration information to another device, where the configuration information specifies how to adjust parameters based on user input to the user-defined music control element. Disclosed techniques may facilitate centralized learning for human-like music production while allowing individualized customization for individual users. Further, disclosed techniques may allow artists to define their own abstract music controls and make those controls available to end-users.

Abstract: Techniques are disclosed relating to automatically generating new music content based on image representations of audio files. A music generation system includes a music generation subsystem and a music classification subsystem. The music generation subsystem may generate output music content according to music parameters that define policy for generating music. The classification subsystem may be used to classify whether music is generated by the music generation subsystem or is professionally produced music content. The music generation subsystem may implement an algorithm that is reinforced by prediction output from the music classification subsystem. Reinforcement may include tuning the music parameters to generate more human-like music content.

Abstract: Techniques are disclosed that pertain to generating output music content based on musical embeddings. A computer system generates output music content that includes multiple overlapping musical expressions in time. The computer system receives user feedback at a point in time while the output music content is being played. Based on the user feedback and based on characteristics of the output music content associated with the point in time, the computer system determines one or more expression embeddings generated based on expressions selected for inclusion in the output music content and one or more composition embeddings generated based on combined expressions in the output music content. The computer system generates additional output music content based on the expression and composition embeddings.

Abstract: Techniques are disclosed that pertain to training a machine learning model to generate audio data similar to a music generator program. A computer system, executing a rules-based music generator program, selects and combines multiple musical expressions to generate audio data. The computer system trains a machine learning model to select and combine musical expressions to generate music compositions. The machine learning model receives generator information by the generator program that indicates expression selection decisions to generate the audio data, mixing decisions to generate the audio data, and first audio information output based on the generator program's expression selection decisions and the mixing decisions. The computer system compares the generator information to expression selection decisions, mixing decisions, and second audio information generated by the machine learning model based on the machine learning model's expression selection decisions and mixing decisions.

Abstract: Techniques are disclosed relating to automatically generate new music content based on image representations of audio files. A computer system generate image representations of audio files. The image representations may be generated, for example, based on data in the audio files and MIDI representations of the audio files. Audio files for combination may then be selected based on analysis of the image representations. For example, image-based machine learning algorithms may be implemented to assess the image representations and select music for combining.

Abstract: Techniques are disclosed relating to implementing user-created controls to modify music content. A music generator system may be configured to automatically generate output music content by selecting and combining audio tracks based on various parameters. Users may create their own control elements that the music generator system may train (e.g., using AI techniques) to generate output music content according to a user's intended functionality of a user-created control element.

Abstract: Techniques are disclosed relating to implementing audio techniques for real-time audio generation. For example, a music generator system may generate new music content from playback music content based on different parameter representations of an audio signal. In some cases, an audio signal can be represented by both a graph of the signal (e.g., an audio signal graph) relative to time and a graph of the signal relative to beats (e.g., a signal graph). The signal graph is invariant to tempo, which allows for tempo invariant modification of audio parameters of the music content in addition to tempo variant modifications based on the audio signal graph.

Abstract: Techniques are disclosed relating to implementing audio techniques for real-time audio generation. For example, a music generator system may generate new music content from playback music content based on different parameter representations of an audio signal. In some cases, an audio signal can be represented by both a graph of the signal (e.g., an audio signal graph) relative to time and a graph of the signal relative to beats (e.g., a signal graph). The signal graph is invariant to tempo, which allows for tempo invariant modification of audio parameters of the music content in addition to tempo variant modifications based on the audio signal graph.

Abstract: Techniques are disclosed relating to automatically generating new music content based on image representations of audio files. A music generation system includes a music generation subsystem and a music classification subsystem. The music generation subsystem may generate output music content according to music parameters that define policy for generating music. The classification subsystem may be used to classify whether music is generated by the music generation subsystem or is professionally produced music content. The music generation subsystem may implement an algorithm that is reinforced by prediction output from the music classification subsystem. Reinforcement may include tuning the music parameters to generate more human-like music content.

Abstract: Techniques are disclosed relating to automatically generate new music content. In some embodiments, a computing system receivers user input specifying a user-defined music control element. The computing system may train a machine learning model to change both composition and performance parameters based on user adjustments to the user-defined music control element. In embodiments in which composition and performance subsystems are on different devices, one device may transmit configuration information to another device, where the configuration information specifies how to adjust parameters based on user input to the user-defined music control element. Disclosed techniques may facilitate centralized learning for human-like music production while allowing individualized customization for individual users. Further, disclosed techniques may allow artists to define their own abstract music controls and make those controls available to end-users.

Abstract: Techniques are disclosed relating to automatically generate new music content based on image representations of audio files. A computer system generate image representations of audio files. The image representations may be generated, for example, based on data in the audio files and MIDI representations of the audio files. Audio files for combination may then be selected based on analysis of the image representations. For example, image-based machine learning algorithms may be implemented to assess the image representations and select music for combining.

Abstract: Techniques are disclosed relating to tracking contributions to composed music content. In some embodiments, a computer system determines playback data for a music content mix, where the playback data indicates characteristics of playback of the music content mix and the music content mix includes a determined combination of multiple audio tracks. In some embodiments, the system records, in an electronic block-chain ledger data structure, information specifying individual playback data for one or more of the multiple audio tracks in the music content mix. The information specifying individual playback data for an individual audio track may include usage data for the individual audio track and signature information associated with the individual audio track.

Abstract: Techniques are disclosed relating to implementing audio techniques for real-time audio generation. For example, a music generator system may generate new music content from playback music content based on different parameter representations of an audio signal. In some cases, an audio signal can be represented by both a graph of the signal (e.g., an audio signal graph) relative to time and a graph of the signal relative to beats (e.g., a signal graph). The signal graph is invariant to tempo, which allows for tempo invariant modification of audio parameters of the music content in addition to tempo variant modifications based on the audio signal graph.