• Corpus ID: 207794915

Estimating Unobserved Audio Features for Target-Based Orchestration

  title={Estimating Unobserved Audio Features for Target-Based Orchestration},
  author={Jon Gillick and Carmine-Emanuele Cella and David Bamman},
Target-based assisted orchestration can be thought of as the process of searching for optimal combinations of sounds to match a target sound, given a database of samples, a similarity metric, and a set of constraints. A typical solution to this problem is a proposed orchestral score where candidates are ranked by similarity in some feature space between the target sound and the mixture of audio samples in the database corresponding to the notes in the score; in the orchestral setting, valid… 
OrchideaSOL: a dataset of extended instrumental techniques for computer-aided orchestration
OrchideaSOL is a reduced and modified subset of Studio On Line, or SOL for short, a dataset developed at Ircam between 1996 and 1998 and designed to be used as default dataset for the OrchideA framework for target-based computer-aided orchestration.
Music Information Retrieval and Contemporary Classical Music: A Successful Failure
The story of the relationship of a contemporary music composer with computational tools that are situated in the areas of signal processing, machine learning and music information retrieval (MIR) is shared.
Breaking Speech Recognizers to Imagine Lyrics
A vocal source separation algorithm and an acoustic model trained to recognize isolated speech are repurposed, instead inputting instrumental music or environmental sounds and a transcription of words to be spoken in the input audio is obtained.
nnAudio: An on-the-Fly GPU Audio to Spectrogram Conversion Toolbox Using 1D Convolutional Neural Networks
A new neural network-based audio processing framework with graphics processing unit (GPU) support that leverages 1D convolutional neural networks to perform time domain to frequency domain conversion, which allows on-the-fly spectrogram extraction due to its fast speed, without the need to store any spectrograms on the disk.


Predicting Timbre Features of Instrument Sound Combinations: Application to Automatic Orchestration
A set of functions to predict the timbre features of an instrument sound combination, given the features of the individual components in the mixture, are introduced and the accuracy of these predictors is shown.
Solving the musical orchestration problem using multiobjective constrained optimization with a genetic local search approach
Orchidée is introduced, a time-efficient evolutionary orchestration algorithm that allows the discovery of optimal solutions and favors the exploration of non-intuitive sound mixtures and the innovative CDCSolver repair metaheuristic, thanks to which the search is led towards regions fulfilling a set of musical-related requirements.
Leveraging diversity in computer-aided musical orchestration with an artificial immune system for multi-modal optimization
CAMO-AIS has higher diversity of orchestrations than Orchids without loss of perceptual similarity, and Opt-aiNet was developed to maximize diversity in the solution set of multi-modal optimization problems, which results in multiple alternative orchestrations for the same reference sound that are different among themselves.
Similarity Measures for Vocal-Based Drum Sample Retrieval Using Deep Convolutional Auto-Encoders
This paper uses a linear mixed effect regression model to show how features learned by convolutional auto-encoders perform as predictors for perceptual similarity between sounds, and investigates how the size and shape of the encoded layer effects the predictive power of the learned features.
A perceptually orientated approach for automatic classification of timbre content of orchestral excerpts
In this paper, we report on the development of a perceptually orientated and automatic classification system of timbre content within orchestral audio samples. Here, we have decided to investigate
Timbre as a structuring force in music
This work seeks to develop a theoretical ground for orchestration practice starting with the structuring role that timbre can play in music, and examines how such principles might be incorporated into computer-aided orchestration systems and computer- aided orchestral rendering systems.
OpenMIC-2018: An Open Data-set for Multiple Instrument Recognition
The construction of a new, open data-set for multi-instrument recognition, which contains 20,000 examples of Creative Commons-licensed music available on the Free Music Archive, and how the instrument taxonomy was constructed is described.
Design and Architecture of Distributed Sound Processing and Database Systems for Web-Based Computer Music Applications
The design and architecture of distributed and World Wide Web-based computer music applications is discussed, based on the experiences of the Studio On-Line project begun in 1995 at IRCAM, Institut de Recherche et Coordination Acoustique Musique, Paris.
A Semantic Approach To Autonomous Mixing
A system where processing parameters for music production are inferred from instrument-specific rules rather than low-level features is proposed, and a body of rules from practical mixing engineering literature is compiled to assess the potential of a system using just these rules.
Audio-Visual Scene Analysis with Self-Supervised Multisensory Features
It is argued that the visual and audio components of a video signal should be modeled jointly using a fused multisensory representation, and it is proposed to learn such a representation in a self-supervised way, by training a neural network to predict whether video frames and audio are temporally aligned.