Shlomo Dubnov

Hao-Wen Dong, Ke Chen, Shlomo Dubnov et al.

Existing approaches for generating multitrack music with transformer models have been limited in terms of the number of instruments, the length of the music segments and slow inference. This is partly due to the memory requirements of the lengthy input sequences necessitated by existing representations. In this work, we propose a new multitrack music representation that allows a diverse set of instruments while keeping a short sequence length. Our proposed Multitrack Music Transformer (MMT) achieves comparable performance with state-of-the-art systems, landing in between two recently proposed models in a subjective listening test, while achieving substantial speedups and memory reductions over both, making the method attractive for real time improvisation or near real time creative applications. Further, we propose a new measure for analyzing musical self-attention and show that the trained model attends more to notes that form a consonant interval with the current note and to notes that are 4N beats away from the current step.

Ke Chen, Yusong Wu, Haohe Liu et al.

Diffusion models have shown promising results in cross-modal generation tasks, including text-to-image and text-to-audio generation. However, generating music, as a special type of audio, presents unique challenges due to limited availability of music data and sensitive issues related to copyright and plagiarism. In this paper, to tackle these challenges, we first construct a state-of-the-art text-to-music model, MusicLDM, that adapts Stable Diffusion and AudioLDM architectures to the music domain. We achieve this by retraining the contrastive language-audio pretraining model (CLAP) and the Hifi-GAN vocoder, as components of MusicLDM, on a collection of music data samples. Then, to address the limitations of training data and to avoid plagiarism, we leverage a beat tracking model and propose two different mixup strategies for data augmentation: beat-synchronous audio mixup and beat-synchronous latent mixup, which recombine training audio directly or via a latent embeddings space, respectively. Such mixup strategies encourage the model to interpolate between musical training samples and generate new music within the convex hull of the training data, making the generated music more diverse while still staying faithful to the corresponding style. In addition to popular evaluation metrics, we design several new evaluation metrics based on CLAP score to demonstrate that our proposed MusicLDM and beat-synchronous mixup strategies improve both the quality and novelty of generated music, as well as the correspondence between input text and generated music.

Paarth Neekhara, Shehzeen Hussain, Rafael Valle et al.

We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on factorizing speech into explicitly disentangled representations that separately encode speaker characteristics and linguistic content. However, disentangling speech representations to capture such attributes using task-specific loss terms can lead to information loss. In this work, instead of explicitly disentangling attributes with loss terms, we present a framework to train a controllable voice conversion model on entangled speech representations derived from self-supervised learning (SSL) and speaker verification models. First, we develop techniques to derive prosodic information from the audio signal and SSL representations to train predictive submodules in the synthesis model. Next, we propose a training strategy to iteratively improve the synthesis model for voice conversion, by creating a challenging training objective using self-synthesized examples. We demonstrate that incorporating such self-synthesized examples during training improves the speaker similarity of generated speech as compared to a baseline voice conversion model trained solely on heuristically perturbed inputs. Our framework is trained without any text and achieves state-of-the-art results in zero-shot voice conversion on metrics evaluating naturalness, speaker similarity, and intelligibility of synthesized audio.

Tornike Karchkhadze, Shlomo Dubnov

We present a framework for real-time human-AI musical co-performance, in which a latent diffusion model generates instrumental accompaniment in response to a live stream of context audio. The system combines a MAX/MSP front-end-handling real-time audio input, buffering, and playback-with a Python inference server running the generative model, communicating via OSC/UDP messages. This allows musicians to perform in MAX/MSP - a well-established, real-time capable environment - while interacting with a large-scale Python-based generative model, overcoming the fundamental disconnect between real-time music tools and state-of-the-art AI models. We formulate accompaniment generation as a sliding-window look-ahead protocol, training the model to predict future audio from partial context, where system latency is a critical constraint. To reduce latency, we apply consistency distillation to our diffusion model, achieving a 5.4x reduction in sampling time, with both models achieving real-time operation. Evaluated on musical coherence, beat alignment, and audio quality, both models achieve strong performance in the Retrospective regime and degrade gracefully as look-ahead increases. These results demonstrate the feasibility of diffusion-based real-time accompaniment and expose the fundamental trade-off between model latency, look-ahead depth, and generation quality that any such system must navigate.

Ke Chen, Jiaqi Su, Taylor Berg-Kirkpatrick et al.

Achieving robust speech separation for overlapping speakers in various acoustic environments with noise and reverberation remains an open challenge. Although existing datasets are available to train separators for specific scenarios, they do not effectively generalize across diverse real-world scenarios. In this paper, we present a novel data simulation pipeline that produces diverse training data from a range of acoustic environments and content, and propose new training paradigms to improve quality of a general speech separation model. Specifically, we first introduce AC-SIM, a data simulation pipeline that incorporates broad variations in both content and acoustics. Then we integrate multiple training objectives into the permutation invariant training (PIT) to enhance separation quality and generalization of the trained model. Finally, we conduct comprehensive objective and human listening experiments across separation architectures and benchmarks to validate our methods, demonstrating substantial improvement of generalization on both non-homologous and real-world test sets.

Keren Shao, Ke Chen, Taylor Berg-Kirkpatrick et al.

In deep learning research, many melody extraction models rely on redesigning neural network architectures to improve performance. In this paper, we propose an input feature modification and a training objective modification based on two assumptions. First, harmonics in the spectrograms of audio data decay rapidly along the frequency axis. To enhance the model's sensitivity on the trailing harmonics, we modify the Combined Frequency and Periodicity (CFP) representation using discrete z-transform. Second, the vocal and non-vocal segments with extremely short duration are uncommon. To ensure a more stable melody contour, we design a differentiable loss function that prevents the model from predicting such segments. We apply these modifications to several models, including MSNet, FTANet, and a newly introduced model, PianoNet, modified from a piano transcription network. Our experimental results demonstrate that the proposed modifications are empirically effective for singing melody extraction.

Ross Greer, Laura Fleig, Shlomo Dubnov

This paper explores the integration of visual communication and musical interaction by implementing a robotic camera within a "Guided Harmony" musical game. We aim to examine co-creative behaviors between human musicians and robotic systems. Our research explores existing methodologies like improvisational game pieces and extends these concepts to include robotic participation using a PTZ camera. The robotic system interprets and responds to nonverbal cues from musicians, creating a collaborative and adaptive musical experience. This initial case study underscores the importance of intuitive visual communication channels. We also propose future research directions, including parameters for refining the visual cue toolkit and data collection methods to understand human-machine co-creativity further. Our findings contribute to the broader understanding of machine intelligence in augmenting human creativity, particularly in musical settings.

Tornike Karchkhadze, Mohammad Rasool Izadi, Shuo Zhang et al.

In this work, we propose an approach to music source separation that uses a generative diffusion model as a last-stage refinement on top of a deterministic separator, progressively enhancing the separated sources through iterative denoising. While the diffusion refinement yields measurable quality gains, it requires iterative steps at inference, increasing computational cost. To speed up the inference process, we apply consistency distillation, reducing inference to a single step while maintaining quality; with two or more steps, the distilled model even surpasses the diffusion-based approach. Crucially, our method is architecture-agnostic: we demonstrate state-of-the-art results when applied to both a custom U-Net-based separator on Slakh2100 and the state-of-the-art BS-RoFormer model on MUSDB18, showing that the refinement generalizes across backbone architectures. Sound examples are available at: https://consistency-separation.github.io/.

Keren Shao, Ke Chen, Matthew Baas et al.

Robustness is critical in zero-shot singing voice conversion (SVC). This paper introduces two novel methods to strengthen the robustness of the kNN-VC framework for SVC. First, kNN-VC's core representation, WavLM, lacks harmonic emphasis, resulting in dull sounds and ringing artifacts. To address this, we leverage the bijection between WavLM, pitch contours, and spectrograms to perform additive synthesis, integrating the resulting waveform into the model to mitigate these issues. Second, kNN-VC overlooks concatenative smoothness, a key perceptual factor in SVC. To enhance smoothness, we propose a new distance metric that filters out unsuitable kNN candidates and optimize the summing weights of the candidates during inference. Although our techniques are built on the kNN-VC framework for implementation convenience, they are broadly applicable to general concatenative neural synthesis models. Experimental results validate the effectiveness of these modifications in achieving robust SVC. Demo: http://knnsvc.com Code: https://github.com/SmoothKen/knn-svc

Vignesh Gokul, Shlomo Dubnov

Deep learning models require large amounts of clean data to acheive good performance. To avoid the cost of expensive data acquisition, researchers use the abundant data available on the internet. This raises significant privacy concerns on the potential misuse of personal data for model training without authorisation. Recent works such as CUDA propose solutions to this problem by adding class-wise blurs to make datasets unlearnable, i.e a model can never use the acquired dataset for learning. However these methods often reduce the quality of the data making it useless for practical applications. We introduce PosCUDA, a position based convolution for creating unlearnable audio datasets. PosCUDA uses class-wise convolutions on small patches of audio. The location of the patches are based on a private key for each class, hence the model learns the relations between positional blurs and labels, while failing to generalize. We empirically show that PosCUDA can achieve unlearnability while maintaining the quality of the original audio datasets. Our proposed method is also robust to different audio feature representations such as MFCC, raw audio and different architectures such as transformers, convolutional networks etc.

Keren Shao, Ke Chen, Shlomo Dubnov

In this challenge, we disentangle the deep filters from the original DeepfilterNet and incorporate them into our Spec-UNet-based network to further improve a hybrid Demucs (hdemucs) based remixing pipeline. The motivation behind the use of the deep filter component lies at its potential in better handling temporal fine structures. We demonstrate an incremental improvement in both the Signal-to-Distortion Ratio (SDR) and the Hearing Aid Audio Quality Index (HAAQI) metrics when comparing the performance of hdemucs against different versions of our model.

Mingyang Yao, Ke Chen, Shlomo Dubnov et al.

Automatic chord recognition (ACR) via deep learning models has gradually achieved promising recognition accuracy, yet two key challenges remain. First, prior work has primarily focused on audio-domain ACR, while symbolic music (e.g., score) ACR has received limited attention due to data scarcity. Second, existing methods still overlook strategies that are aligned with human music analytical practices. To address these challenges, we make two contributions: (1) we introduce POP909-CL, an enhanced version of POP909 dataset with tempo-aligned content and human-corrected labels of chords, beats, keys, and time signatures; and (2) We propose BACHI, a symbolic chord recognition model that decomposes the task into different decision steps, namely boundary detection and iterative ranking of chord root, quality, and bass (inversion). This mechanism mirrors the human ear-training practices. Experiments demonstrate that BACHI achieves state-of-the-art chord recognition performance on both classical and pop music benchmarks, with ablation studies validating the effectiveness of each module.

Ilana Shapiro, Ruanqianqian Huang, Zachary Novack et al.

Western music is an innately hierarchical system of interacting levels of structure, from fine-grained melody to high-level form. In order to analyze music compositions holistically and at multiple granularities, we propose a unified, hierarchical meta-representation of musical structure called the structural temporal graph (STG). For a single piece, the STG is a data structure that defines a hierarchy of progressively finer structural musical features and the temporal relationships between them. We use the STG to enable a novel approach for deriving a representative structural summary of a music corpus, which we formalize as a nested NP-hard combinatorial optimization problem extending the Generalized Median Graph problem. Our approach first applies simulated annealing to develop a measure of structural distance between two music pieces rooted in graph isomorphism. Our approach then combines the formal guarantees of SMT solvers with nested simulated annealing over structural distances to produce a structurally sound, representative centroid STG for an entire corpus of STGs from individual pieces. To evaluate our approach, we conduct experiments verifying that structural distance accurately differentiates between music pieces, and that derived centroids accurately structurally characterize their corpora.

Tornike Karchkhadze, Keren Shao, Shlomo Dubnov

This work presents a novel method for composing and improvising music inspired by Cornelius Cardew's Treatise, using AI to bridge graphic notation and musical expression. By leveraging OpenAI's ChatGPT to interpret the abstract visual elements of Treatise, we convert these graphical images into descriptive textual prompts. These prompts are then input into MusicLDM, a pre-trained latent diffusion model designed for music generation. We introduce a technique called "outpainting," which overlaps sections of AI-generated music to create a seamless and cohesive composition. We demostrate a new perspective on performing and interpreting graphic scores, showing how AI can transform visual stimuli into sound and expand the creative possibilities in contemporary/experimental music composition. Musical pieces are available at https://bit.ly/TreatiseAI

Vignesh Gokul, Chris Francis, Shlomo Dubnov

Co-creativity in music refers to two or more musicians or musical agents interacting with one another by composing or improvising music. However, this is a very subjective process and each musician has their own preference as to which improvisation is better for some context. In this paper, we aim to create a measure based on total information flow to quantitatively evaluate the co-creativity process in music. In other words, our measure is an indication of how "good" a creative musical process is. Our main hypothesis is that a good musical creation would maximize information flow between the participants captured by music voices recorded in separate tracks. We propose a method to compute the information flow using pre-trained generative models as entropy estimators. We demonstrate how our method matches with human perception using a qualitative study.

Ke Chen, Shuai Yu, Cheng-i Wang et al.

Singing melody extraction is an important problem in the field of music information retrieval. Existing methods typically rely on frequency-domain representations to estimate the sung frequencies. However, this design does not lead to human-level performance in the perception of melody information for both tone (pitch-class) and octave. In this paper, we propose TONet, a plug-and-play model that improves both tone and octave perceptions by leveraging a novel input representation and a novel network architecture. First, we present an improved input representation, the Tone-CFP, that explicitly groups harmonics via a rearrangement of frequency-bins. Second, we introduce an encoder-decoder architecture that is designed to obtain a salience feature map, a tone feature map, and an octave feature map. Third, we propose a tone-octave fusion mechanism to improve the final salience feature map. Experiments are done to verify the capability of TONet with various baseline backbone models. Our results show that tone-octave fusion with Tone-CFP can significantly improve the singing voice extraction performance across various datasets -- with substantial gains in octave and tone accuracy.

Ke Chen, Xingjian Du, Bilei Zhu et al.

Audio classification is an important task of mapping audio samples into their corresponding labels. Recently, the transformer model with self-attention mechanisms has been adopted in this field. However, existing audio transformers require large GPU memories and long training time, meanwhile relying on pretrained vision models to achieve high performance, which limits the model's scalability in audio tasks. To combat these problems, we introduce HTS-AT: an audio transformer with a hierarchical structure to reduce the model size and training time. It is further combined with a token-semantic module to map final outputs into class featuremaps, thus enabling the model for the audio event detection (i.e. localization in time). We evaluate HTS-AT on three datasets of audio classification where it achieves new state-of-the-art (SOTA) results on AudioSet and ESC-50, and equals the SOTA on Speech Command V2. It also achieves better performance in event localization than the previous CNN-based models. Moreover, HTS-AT requires only 35% model parameters and 15% training time of the previous audio transformer. These results demonstrate the high performance and high efficiency of HTS-AT.

Ke Chen, Xingjian Du, Bilei Zhu et al.

Deep learning techniques for separating audio into different sound sources face several challenges. Standard architectures require training separate models for different types of audio sources. Although some universal separators employ a single model to target multiple sources, they have difficulty generalizing to unseen sources. In this paper, we propose a three-component pipeline to train a universal audio source separator from a large, but weakly-labeled dataset: AudioSet. First, we propose a transformer-based sound event detection system for processing weakly-labeled training data. Second, we devise a query-based audio separation model that leverages this data for model training. Third, we design a latent embedding processor to encode queries that specify audio targets for separation, allowing for zero-shot generalization. Our approach uses a single model for source separation of multiple sound types, and relies solely on weakly-labeled data for training. In addition, the proposed audio separator can be used in a zero-shot setting, learning to separate types of audio sources that were never seen in training. To evaluate the separation performance, we test our model on MUSDB18, while training on the disjoint AudioSet. We further verify the zero-shot performance by conducting another experiment on audio source types that are held-out from training. The model achieves comparable Source-to-Distortion Ratio (SDR) performance to current supervised models in both cases.

Shlomo Dubnov, Kevin Huang, Cheng-i Wang

A music piece is both comprehended hierarchically, from sonic events to melodies, and sequentially, in the form of repetition and variation. Music from different cultures establish different aesthetics by having different style conventions on these two aspects. We propose a framework that could be used to quantitatively compare music from different cultures by looking at these two aspects. The framework is based on an Music Information Dynamics model, a Variable Markov Oracle (VMO), and is extended with a variational representation learning of audio. A variational autoencoder (VAE) is trained to map audio fragments into a latent representation. The latent representation is fed into a VMO. The VMO then learns a clustering of the latent representation via a threshold that maximizes the information rate of the quantized latent representation sequence. This threshold effectively controls the sensibility of the predictive step to acoustic changes, which determines the framework's ability to track repetitions on longer time scales. This approach allows characterization of the overall information contents of a musical signal at each level of acoustic sensibility. Our findings under this framework show that sensibility to subtle acoustic changes is higher for East-Asian musical traditions, while the Western works exhibit longer motivic structures at higher thresholds of differences in the latent space. This suggests that a profile of information contents, analyzed as a function of the level of acoustic detail can serve as a possible cultural characteristic.

Ross Greer, Shlomo Dubnov

Nonverbal communication, in particular eye contact, is a critical element of the music classroom, shown to keep students on task, coordinate musical flow, and communicate improvisational ideas. Unfortunately, this nonverbal aspect to performance and pedagogy is lost in the virtual classroom. In this paper, we propose a machine learning system which uses single instance, single camera image frames as input to estimate the gaze target of a user seated in front of their computer, augmenting the user's video feed with a display of the estimated gaze target and thereby restoring nonverbal communication of directed gaze. The proposed estimation system consists of modular machine learning blocks, leading to a target-oriented (rather than coordinate-oriented) gaze prediction. We instantiate one such example of the complete system to run a pilot study in a virtual music classroom over Zoom software. Inference time and accuracy meet benchmarks for videoconferencing applications, and quantitative and qualitative results of pilot experiments include improved success of cue interpretation and student-reported formation of collaborative, communicative relationships between conductor and musician.

Eunjeong Koh, Shlomo Dubnov

Emotion is a complicated notion present in music that is hard to capture even with fine-tuned feature engineering. In this paper, we investigate the utility of state-of-the-art pre-trained deep audio embedding methods to be used in the Music Emotion Recognition (MER) task. Deep audio embedding methods allow us to efficiently capture the high dimensional features into a compact representation. We implement several multi-class classifiers with deep audio embeddings to predict emotion semantics in music. We investigate the effectiveness of L3-Net and VGGish deep audio embedding methods for music emotion inference over four music datasets. The experiments with several classifiers on the task show that the deep audio embedding solutions can improve the performances of the previous baseline MER models. We conclude that deep audio embeddings represent musical emotion semantics for the MER task without expert human engineering.

Vaikkunth Mugunthan, Vignesh Gokul, Lalana Kagal et al.

Federated Generative Adversarial Network (FedGAN) is a communication-efficient approach to train a GAN across distributed clients without clients having to share their sensitive training data. In this paper, we experimentally show that FedGAN generates biased data points under non-independent-and-identically-distributed (non-iid) settings. Also, we propose Bias-Free FedGAN, an approach to generate bias-free synthetic datasets using FedGAN. Our approach generates metadata at the aggregator using the models received from clients and retrains the federated model to achieve bias-free results for image synthesis. Bias-Free FedGAN has the same communication cost as that of FedGAN. Experimental results on image datasets (MNIST and FashionMNIST) validate our claims.

Shehzeen Hussain, Paarth Neekhara, Shlomo Dubnov et al.

There has been a recent surge in adversarial attacks on deep learning based automatic speech recognition (ASR) systems. These attacks pose new challenges to deep learning security and have raised significant concerns in deploying ASR systems in safety-critical applications. In this work, we introduce WaveGuard: a framework for detecting adversarial inputs that are crafted to attack ASR systems. Our framework incorporates audio transformation functions and analyses the ASR transcriptions of the original and transformed audio to detect adversarial inputs. We demonstrate that our defense framework is able to reliably detect adversarial examples constructed by four recent audio adversarial attacks, with a variety of audio transformation functions. With careful regard for best practices in defense evaluations, we analyze our proposed defense and its strength to withstand adaptive and robust attacks in the audio domain. We empirically demonstrate that audio transformations that recover audio from perceptually informed representations can lead to a strong defense that is robust against an adaptive adversary even in a complete white-box setting. Furthermore, WaveGuard can be used out-of-the box and integrated directly with any ASR model to efficiently detect audio adversarial examples, without the need for model retraining.

Paarth Neekhara, Shehzeen Hussain, Jinglong Du et al.

With the abundance of large-scale deep learning models, it has become possible to repurpose pre-trained networks for new tasks. Recent works on adversarial reprogramming have shown that it is possible to repurpose neural networks for alternate tasks without modifying the network architecture or parameters. However these works only consider original and target tasks within the same data domain. In this work, we broaden the scope of adversarial reprogramming beyond the data modality of the original task. We analyze the feasibility of adversarially repurposing image classification neural networks for Natural Language Processing (NLP) and other sequence classification tasks. We design an efficient adversarial program that maps a sequence of discrete tokens into an image which can be classified to the desired class by an image classification model. We demonstrate that by using highly efficient adversarial programs, we can reprogram image classifiers to achieve competitive performance on a variety of text and sequence classification benchmarks without retraining the network.

Shlomo Dubnov

Music comprises of a set of complex simultaneous events organized in time. In this paper we introduce a novel framework that we call Deep Musical Information Dynamics, which combines two parallel streams - a low rate latent representation stream that is assumed to capture the dynamics of a thought process contrasted with a higher rate information dynamics derived from the musical data itself. Motivated by rate-distortion theories of human cognition we propose a framework for exploring possible relations between imaginary anticipations existing in the listener's mind and information dynamics of the musical surface itself. This model is demonstrated for the case of symbolic (MIDI) data, as accounting for acoustic surface would require many more layers to capture instrument properties and performance expressive inflections. The mathematical framework is based on variational encoding that first establishes a high rate representation of the musical observations, which is then reduced using a bit-allocation method into a parallel low rate data stream. The combined loss considered here includes both the information rate in terms of time evolution for each stream, and the fidelity of encoding measured in terms of mutual information between the high and low rate representations. In the simulations presented in the paper we are able to juxtapose aspects of latent/imaginary surprisal versus surprisal of the music surface in a manner that is quantifiable and computationally tractable. The set of computational tools is discussed in the paper, suggesting that a trade off between compression and prediction are an important factor in the analysis and design of time-based music generative models.

Paarth Neekhara, Shehzeen Hussain, Shlomo Dubnov et al.

Voice cloning is the task of learning to synthesize the voice of an unseen speaker from a few samples. While current voice cloning methods achieve promising results in Text-to-Speech (TTS) synthesis for a new voice, these approaches lack the ability to control the expressiveness of synthesized audio. In this work, we propose a controllable voice cloning method that allows fine-grained control over various style aspects of the synthesized speech for an unseen speaker. We achieve this by explicitly conditioning the speech synthesis model on a speaker encoding, pitch contour and latent style tokens during training. Through both quantitative and qualitative evaluations, we show that our framework can be used for various expressive voice cloning tasks using only a few transcribed or untranscribed speech samples for a new speaker. These cloning tasks include style transfer from a reference speech, synthesizing speech directly from text, and fine-grained style control by manipulating the style conditioning variables during inference.

Vaikkunth Mugunthan, Vignesh Gokul, Lalana Kagal et al.

Generative Adversarial Networks (GANs) are deep learning architectures capable of generating synthetic datasets. Despite producing high-quality synthetic images, the default GAN has no control over the kinds of images it generates. The Information Maximizing GAN (InfoGAN) is a variant of the default GAN that introduces feature-control variables that are automatically learned by the framework, hence providing greater control over the different kinds of images produced. Due to the high model complexity of InfoGAN, the generative distribution tends to be concentrated around the training data points. This is a critical problem as the models may inadvertently expose the sensitive and private information present in the dataset. To address this problem, we propose a differentially private version of InfoGAN (DP-InfoGAN). We also extend our framework to a distributed setting (DPD-InfoGAN) to allow clients to learn different attributes present in other clients' datasets in a privacy-preserving manner. In our experiments, we show that both DP-InfoGAN and DPD-InfoGAN can synthesize high-quality images with flexible control over image attributes while preserving privacy.

Ke Chen, Cheng-i Wang, Taylor Berg-Kirkpatrick et al.

Drawing an analogy with automatic image completion systems, we propose Music SketchNet, a neural network framework that allows users to specify partial musical ideas guiding automatic music generation. We focus on generating the missing measures in incomplete monophonic musical pieces, conditioned on surrounding context, and optionally guided by user-specified pitch and rhythm snippets. First, we introduce SketchVAE, a novel variational autoencoder that explicitly factorizes rhythm and pitch contour to form the basis of our proposed model. Then we introduce two discriminative architectures, SketchInpainter and SketchConnector, that in conjunction perform the guided music completion, filling in representations for the missing measures conditioned on surrounding context and user-specified snippets. We evaluate SketchNet on a standard dataset of Irish folk music and compare with models from recent works. When used for music completion, our approach outperforms the state-of-the-art both in terms of objective metrics and subjective listening tests. Finally, we demonstrate that our model can successfully incorporate user-specified snippets during the generation process.

Ke Chen, Gus Xia, Shlomo Dubnov

Automatic music generation is an interdisciplinary research topic that combines computational creativity and semantic analysis of music to create automatic machine improvisations. An important property of such a system is allowing the user to specify conditions and desired properties of the generated music. In this paper we designed a model for composing melodies given a user specified symbolic scenario combined with a previous music context. We add manual labeled vectors denoting external music quality in terms of chord function that provides a low dimensional representation of the harmonic tension and resolution. Our model is capable of generating long melodies by regarding 8-beat note sequences as basic units, and shares consistent rhythm pattern structure with another specific song. The model contains two stages and requires separate training where the first stage adopts a Conditional Variational Autoencoder (C-VAE) to build a bijection between note sequences and their latent representations, and the second stage adopts long short-term memory networks (LSTM) with structural conditions to continue writing future melodies. We further exploit the disentanglement technique via C-VAE to allow melody generation based on pitch contour information separately from conditioning on rhythm patterns. Finally, we evaluate the proposed model using quantitative analysis of rhythm and the subjective listening study. Results show that the music generated by our model tends to have salient repetition structures, rich motives, and stable rhythm patterns. The ability to generate longer and more structural phrases from disentangled representations combined with semantic scenario specification conditions shows a broad application of our model.

Shlomo Dubnov

In this paper we explore techniques for generating new music using a Variational Autoencoder (VAE) neural network that was trained on a corpus of specific style. Instead of randomly sampling the latent states of the network to produce free improvisation, we generate new music by querying the network with musical input in a style different from the training corpus. This allows us to produce new musical output with longer-term structure that blends aspects of the query to the style of the network. In order to control the level of this blending we add a noisy channel between the VAE encoder and decoder using bit-allocation algorithm from communication rate-distortion theory. Our experiments provide new insight into relations between the representational and structural information of latent states and the query signal, suggesting their possible use for composition purposes.

Paarth Neekhara, Shehzeen Hussain, Prakhar Pandey et al.

In this work, we demonstrate the existence of universal adversarial audio perturbations that cause mis-transcription of audio signals by automatic speech recognition (ASR) systems. We propose an algorithm to find a single quasi-imperceptible perturbation, which when added to any arbitrary speech signal, will most likely fool the victim speech recognition model. Our experiments demonstrate the application of our proposed technique by crafting audio-agnostic universal perturbations for the state-of-the-art ASR system -- Mozilla DeepSpeech. Additionally, we show that such perturbations generalize to a significant extent across models that are not available during training, by performing a transferability test on a WaveNet based ASR system.

Paarth Neekhara, Chris Donahue, Miller Puckette et al.

Recent approaches in text-to-speech (TTS) synthesis employ neural network strategies to vocode perceptually-informed spectrogram representations directly into listenable waveforms. Such vocoding procedures create a computational bottleneck in modern TTS pipelines. We propose an alternative approach which utilizes generative adversarial networks (GANs) to learn mappings from perceptually-informed spectrograms to simple magnitude spectrograms which can be heuristically vocoded. Through a user study, we show that our approach significantly outperforms naïve vocoding strategies while being hundreds of times faster than neural network vocoders used in state-of-the-art TTS systems. We also show that our method can be used to achieve state-of-the-art results in unsupervised synthesis of individual words of speech.

Ke Chen, Weilin Zhang, Shlomo Dubnov et al.

With recent breakthroughs in artificial neural networks, deep generative models have become one of the leading techniques for computational creativity. Despite very promising progress on image and short sequence generation, symbolic music generation remains a challenging problem since the structure of compositions are usually complicated. In this study, we attempt to solve the melody generation problem constrained by the given chord progression. This music meta-creation problem can also be incorporated into a plan recognition system with user inputs and predictive structural outputs. In particular, we explore the effect of explicit architectural encoding of musical structure via comparing two sequential generative models: LSTM (a type of RNN) and WaveNet (dilated temporal-CNN). As far as we know, this is the first study of applying WaveNet to symbolic music generation, as well as the first systematic comparison between temporal-CNN and RNN for music generation. We conduct a survey for evaluation in our generations and implemented Variable Markov Oracle in music pattern discovery. Experimental results show that to encode structure more explicitly using a stack of dilated convolution layers improved the performance significantly, and a global encoding of underlying chord progression into the generation procedure gains even more.

Eunjeong Stella Koh, Shlomo Dubnov, Dustin Wright

We present a model for capturing musical features and creating novel sequences of music, called the Convolutional Variational Recurrent Neural Network. To generate sequential data, the model uses an encoder-decoder architecture with latent probabilistic connections to capture the hidden structure of music. Using the sequence-to-sequence model, our generative model can exploit samples from a prior distribution and generate a longer sequence of music. We compare the performance of our proposed model with other types of Neural Networks using the criteria of Information Rate that is implemented by Variable Markov Oracle, a method that allows statistical characterization of musical information dynamics and detection of motifs in a song. Our results suggest that the proposed model has a better statistical resemblance to the musical structure of the training data, which improves the creation of new sequences of music in the style of the originals.

Paarth Neekhara, Shehzeen Hussain, Shlomo Dubnov et al.

Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original network. An adversary in such an attack scenario trains an additive contribution to the inputs to repurpose the neural network for the new classification task. While this reprogramming approach works for neural networks with a continuous input space such as that of images, it is not directly applicable to neural networks trained for tasks such as text classification, where the input space is discrete. Repurposing such classification networks would require the attacker to learn an adversarial program that maps inputs from one discrete space to the other. In this work, we introduce a context-based vocabulary remapping model to reprogram neural networks trained on a specific sequence classification task, for a new sequence classification task desired by the adversary. We propose training procedures for this adversarial program in both white-box and black-box settings. We demonstrate the application of our model by adversarially repurposing various text-classification models including LSTM, bi-directional LSTM and CNN for alternate classification tasks.