Tagging amplicons with tag sequences appended to PCR primers allow the multiplexing of numerous samples for high-throughput sequencing (HTS). This approach is routinely used in HTS-based diversity analyses, especially in microbial ecology and biomedical diagnostics. However, amplicon library preparation is subject to pervasive sample sequence cross-contaminations as a result of tag switching events referred to as mistagging. Here, we sequenced seven amplicon libraries prepared using various multiplexing designs in order to measure the magnitude of this phenomenon and its impact on diversity analyses. Up to 28.2% of the unique sequences correspond to undetectable (critical) mistags in single- or saturated double-tagging libraries. We show the advantage of multiplexing samples following Latin Square Designs in order to optimize the detection of mistags and maximize the information on their distribution across samples. We use this information in designs incorporating PCR replicates to filter the critical mistags and to recover the exact composition of mock community samples. Being parameter-free and data-driven, our approach can provide more accurate and reproducible HTS data sets, improving the reliability of their interpretations.

The ubiquity of sound synthesizers has reshaped modern music production, and novel music genres are now sometimes even entirely defined by their use. However, the increasing complexity and number of parameters in modern synthesizers make them extremely hard to master. Hence, the development of methods allowing to easily create and explore with synthesizers is a crucial need. Recently, we introduced a novel formulation of audio synthesizer control based on learning an organized latent audio space of the synthesizer’s capabilities, while constructing an invertible mapping to the space of its parameters. We showed that this formulation allows to simultaneously address automatic parameters inference, macro-control learning, and audio-based preset exploration within a single model. We showed that this formulation can be efficiently addressed by relying on Variational Auto-Encoders (VAE) and Normalizing Flows (NF). In this paper, we extend our results by evaluating our proposal on larger sets of parameters and show its superiority in both parameter inference and audio reconstruction against various baseline models. Furthermore, we introduce disentangling flows, which allow to learn the invertible mapping between two separate latent spaces, while steering the organization of some latent dimensions to match target variation factors by splitting the objective as partial density evaluation. We show that the model disentangles the major factors of audio variations as latent dimensions, which can be directly used as macro-parameters. We also show that our model is able to learn semantic controls of a synthesizer, while smoothly mapping to its parameters. Finally, we introduce an open-source implementation of our models inside a real-time Max4Live device that is readily available to evaluate creative applications of our proposal.

Deep generative models applied to audio have improved by a large margin the state-of-the-art in many speech and music related tasks. However, as raw waveform modelling remains an inherently difficult task, audio generative models are either computationally intensive, rely on low sampling rates, are complicated to control or restrict the nature of possible signals. Among those models, Variational AutoEncoders (VAE) give control over the generation by exposing latent variables, although they usually suffer from low synthesis quality. In this paper, we introduce a Realtime Audio Variational autoEncoder (RAVE) allowing both fast and high-quality audio waveform synthesis. We introduce a novel two-stage training procedure, namely representation learning and adversarial fine-tuning. We show that using a post-training analysis of the latent space allows a direct control between the reconstruction fidelity and the representation compactness. By leveraging a multi-band decomposition of the raw waveform, we show that our model is the first able to generate 48kHz audio signals, while simultaneously running 20 times faster than real-time on a standard laptop CPU. We evaluate synthesis quality using both quantitative and qualitative subjective experiments and show the superiority of our approach compared to existing models. Finally, we present applications of our model for timbre transfer and signal compression. All of our source code and audio examples are publicly available.

In recent years, significant advances have been made in deep learning models for audio generation, offering promising tools for musical creation. In this work, we investigate the use of deep audio generative models in interactive dance/music performance. We adopted a performance-led research design approach, establishing an art-research collaboration between a researcher/musician and a dancer. First, we describe our motion-sound interactive system integrating deep audio generative model and propose three methods for embodied exploration of deep latent spaces. Then, we detail the creative process for building the performance centered on the co-design of the system. Finally, we report feedback from the dancer’s interviews and discuss the results and perspectives. The code implementation is publicly available on our github1.

Recently, the field of musical co-creativity has gained some momentum. In this context, our goal is twofold: to develop an intelligent listening and predictive module of chord sequences, and to propose an adapted evaluation of the associated Music Information Retrieval (MIR) tasks that are the real-time extraction of musical chord labels from a live audio stream and the prediction of a possible continuation of the extracted symbolic sequence. Indeed, this application case invites us to raise questions about the evaluation processes and methodology that are currently applied to chord-based MIR models. In this paper, we focus on musical chords since these mid-level features are frequently used to describe harmonic progressions in Western music. In the case of chords, there exists some strong inherent hierarchical and functional relationships. However, most of the research in the field of MIR focuses mainly on the performance of chord-based statistical models, without considering music-based evaluation or learning. Indeed, usual evaluations are based on a binary qualification of the classification outputs (right chord predicted versus wrong chord predicted). Therefore, we present a specifically-tailored chord analyser to measure the performances of chord-based models in terms of functional qualification of the classification outputs (by taking into account the harmonic function of the chords). Then, in order to introduce musical knowledge into the learning process for the automatic chord extraction task, we propose a specific musical distance for comparing predicted and labeled chords. Finally, we conduct investigations into the impact of including high-level metadata in chord sequence prediction learning (such as information on key or downbeat position). We show that a model can obtain better performances in terms of accuracy or perplexity, but output biased results. At the same time, a model with a lower accuracy score can output errors with more musical meaning. Therefore, performing a goal-oriented evaluation allows a better understanding of the results and a more adapted design of MIR models.

The problem of target-based computer-aided orchestration is a recurring topic in the contemporary music community. Because of its complexity, computer-aided orchestration remains a partially unsolved problem and several systems have been developed in the last twenty years. This article presents a practical overview of the recently introduced Orchidea framework for dynamic computer-aided target-based orchestration. Orchidea continues the line of tools dedicated to the subject (the so-called Orchid* family) originally developed at the Institut de Recherche et Coordination Acoustique/Musique in Paris. Unlike its predecessors, Orchidea uses a combination of optimization techniques that include stochastic matching pursuit, long short-term memory neural networks, and monoobjective evolutionary optimization, with a specifically designed cost function. Symbolic constraints can be integrated in the cost function, and temporally evolving sounds are handled by segmenting them into a set of static targets optimized jointly and then connected. Orchidea is deployed in three different ways: a standalone application, designed to streamline a simplified compositional workflow; a Max package, targeted at composers willing to connect target-based orchestration to the more general area of computer-aided composition; and a set of command-line tools, mostly intended for research purposes and batch processing. The main aim of this article is to present an overview of such software systems and show several instances of the Orchidea framework's application in recent musical productions, tracing the path for future research on the subject.