Download Generative timbre spaces: regularizing variational auto-encoders with perceptual metrics
Timbre spaces have been used in music perception to study the perceptual relationships between instruments based on dissimilarity ratings. However, these spaces do not generalize to novel examples and do not provide an invertible mapping, preventing audio synthesis. In parallel, generative models have aimed to provide methods for synthesizing novel timbres. However, these systems do not provide an understanding of their inner workings and are usually not related to any perceptually relevant information. Here, we show that Variational Auto-Encoders (VAE) can alleviate all of these limitations by constructing generative timbre spaces. To do so, we adapt VAEs to learn an audio latent space, while using perceptual ratings from timbre studies to regularize the organization of this space. The resulting space allows us to analyze novel instruments, while being able to synthesize audio from any point of this space. We introduce a specific regularization allowing to enforce any given similarity distances onto these spaces. We show that the resulting space provide almost similar distance relationships as timbre spaces. We evaluate several spectral transforms and show that the Non-Stationary Gabor Transform (NSGT) provides the highest correlation to timbre spaces and the best quality of synthesis. Furthermore, we show that these spaces can generalize to novel instruments and can generate any path between instruments to understand their timbre relationships. As these spaces are continuous, we study how audio descriptors behave along the latent dimensions. We show that even though descriptors have an overall non-linear topology, they follow a locally smooth evolution. Based on this, we introduce a method for descriptor-based synthesis and show that we can control the descriptors of an instrument while keeping its timbre structure.
Download Assisted Sound Sample Generation with Musical Conditioning in Adversarial Auto-Encoders
Deep generative neural networks have thrived in the field of computer vision, enabling unprecedented intelligent image processes. Yet the results in audio remain less advanced and many applications are still to be investigated. Our project targets real-time sound synthesis from a reduced set of high-level parameters, including semantic controls that can be adapted to different sound libraries and specific tags. These generative variables should allow expressive modulations of target musical qualities and continuously mix into new styles. To this extent we train auto-encoders on an orchestral database of individual note samples, along with their intrinsic attributes: note class, timbre domain (an instrument subset) and extended playing techniques. We condition the decoder for explicit control over the rendered note attributes and use latent adversarial training for learning expressive style parameters that can ultimately be mixed. We evaluate both generative performances and correlations of the attributes with the latent representation. Our ablation study demonstrates the effectiveness of the musical conditioning. The proposed model generates individual notes as magnitude spectrograms from any probabilistic latent code samples (each latent point maps to a single note), with expressive control of orchestral timbres and playing styles. Its training data subsets can directly be visualized in the 3-dimensional latent representation. Waveform rendering can be done offline with the Griffin-Lim algorithm. In order to allow real-time interactions, we fine-tune the decoder with a pretrained magnitude spectrogram inversion network and embed the full waveform generation pipeline in a plugin. Moreover the encoder could be used to process new input samples, after manipulating their latent attribute representation, the decoder can generate sample variations as an audio effect would. Our solution remains rather light-weight and fast to train, it can directly be applied to other sound domains, including an user’s libraries with custom sound tags that could be mapped to specific generative controls. As a result, it fosters creativity and intuitive audio style experimentations. Sound examples and additional visualizations are available on Github1, as well as codes after the review process.
Download Diet Deep Generative Audio Models With Structured Lottery
Deep learning models have provided extremely successful solutions in most audio application fields. However, the high accuracy of these models comes at the expense of a tremendous computation cost. This aspect is almost always overlooked in evaluating the quality of proposed models. However, models should not be evaluated without taking into account their complexity. This aspect is especially critical in audio applications, which heavily relies on specialized embedded hardware with real-time constraints. In this paper, we build on recent observations that deep models are highly overparameterized, by studying the lottery ticket hypothesis on deep generative audio models. This hypothesis states that extremely efficient small sub-networks exist in deep models and would provide higher accuracy than larger models if trained in isolation. However, lottery tickets are found by relying on unstructured masking, which means that resulting models do not provide any gain in either disk size or inference time. Instead, we develop here a method aimed at performing structured trimming. We show that this requires to rely on global selection and introduce a specific criterion based on mutual information. First, we confirm the surprising result that smaller models provide higher accuracy than their large counterparts. We further show that we can remove up to 95% of the model weights without significant degradation in accuracy. Hence, we can obtain very light models for generative audio across popular methods such as Wavenet, SING or DDSP, that are up to 100 times smaller with commensurate accuracy. We study the theoretical bounds for embedding these models on Raspberry Pi and Arduino, and show that we can obtain generative models on CPU with equivalent quality as large GPU models. Finally, we discuss the possibility of implementing deep generative audio models on embedded platforms.