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.
On-device directional hearing requires audio source separation from a given direction while achieving stringent human-imperceptible latency requirements. While neural nets can achieve significantly better performance than traditional beamformers, all existing models fall short of supporting low-latency causal inference on computationally-constrained wearables. We present DeepBeam, a hybrid model that combines traditional beamformers with a custom lightweight neural net. The former reduces the computational burden of the latter and also improves its generalizability, while the latter is designed to further reduce the memory and computational overhead to enable real-time and low-latency operations. Our evaluation shows comparable performance to state-of-the-art causal inference models on synthetic data while achieving a 5x reduction of model size, 4x reduction of computation per second, 5x reduction in processing time and generalizing better to real hardware data. Further, our real-time hybrid model runs in 8 ms on mobile CPUs designed for low-power wearable devices and achieves an end-to-end latency of 17.5 ms.
In this work, we demonstrate how a publicly available, pre-trained Jukebox model can be adapted for the problem of audio source separation from a single mixed audio channel. Our neural network architecture, which is using transfer learning, is quick to train and the results demonstrate performance comparable to other state-of-the-art approaches that require a lot more compute resources, training data, and time. We provide an open-source code implementation of our architecture (https://github.com/wzaielamri/unmix)
Listening to the audio of TV broadcast signals can be challenging for hearing-impaired as well as normal-hearing listeners, especially when background sounds are prominent or too loud compared to the speech signal. This can result in a reduced satisfaction and increased listening effort of the listeners. Since the broadcast sound is usually premixed, we perform a subjective evaluation for quantifying the potential of speech enhancement systems based on audio source separation and recurrent neural networks (RNN). Recently, RNNs have shown promising results in the context of sound source separation and real-time signal processing. In this paper, we separate the speech from the background signals and remix the separated sounds at a higher signal-to-noise ratio. This differs from classic speech enhancement, where usually only the extracted speech signal is exploited. The subjective evaluation with 20 normal-hearing subjects on real TV-broadcast material shows that our proposed enhancement system is able to reduce the listening effort by around 2 points on a 13-point listening effort rating scale and increases the perceived sound quality compared to the original mixture.
We showcase an unsupervised method that repurposes deep models trained for music generation and music tagging for audio source separation, without any retraining. An audio generation model is conditioned on an input mixture, producing a latent encoding of the audio used to generate audio. This generated audio is fed to a pretrained music tagger that creates source labels. The cross-entropy loss between the tag distribution for the generated audio and a predefined distribution for an isolated source is used to guide gradient ascent in the (unchanging) latent space of the generative model. This system does not update the weights of the generative model or the tagger, and only relies on moving through the generative model's latent space to produce separated sources. We use OpenAI's Jukebox as the pretrained generative model, and we couple it with four kinds of pretrained music taggers (two architectures and two tagging datasets). Experimental results on two source separation datasets, show this approach can produce separation estimates for a wider variety of sources than any tested supervised or unsupervised system. This work points to the vast and heretofore untapped potential of large pretrained music models for audio-to-audio tasks like source separation.
The cocktail party problem aims at isolating any source of interest within a complex acoustic scene, and has long inspired audio source separation research. Recent efforts have mainly focused on separating speech from noise, speech from speech, musical instruments from each other, or sound events from each other. However, separating an audio mixture (e.g., movie soundtrack) into the three broad categories of speech, music, and sound effects (understood to include ambient noise and natural sound events) has been left largely unexplored, despite a wide range of potential applications. This paper formalizes this task as the cocktail fork problem, and presents the Divide and Remaster (DnR) dataset to foster research on this topic. DnR is built from three well-established audio datasets (LibriSpeech, FMA, FSD50k), taking care to reproduce conditions similar to professionally produced content in terms of source overlap and relative loudness, and made available at CD quality. We benchmark standard source separation algorithms on DnR, and further introduce a new multi-resolution model to better address the variety of acoustic characteristics of the three source types. Our best model produces SI-SDR improvements over the mixture of 11.0 dB for music, 11.2 dB for speech, and 10.8 dB for sound effects.
State of the art audio source separation models rely on supervised data-driven approaches, which can be expensive in terms of labeling resources. On the other hand, approaches for training these models without any direct supervision are typically high-demanding in terms of memory and time requirements, and remain impractical to be used at inference time. We aim to tackle these limitations by proposing a simple yet effective unsupervised separation algorithm, which operates directly on a latent representation of time-domain signals. Our algorithm relies on deep Bayesian priors in the form of pre-trained autoregressive networks to model the probability distributions of each source. We leverage the low cardinality of the discrete latent space, trained with a novel loss term imposing a precise arithmetic structure on it, to perform exact Bayesian inference without relying on an approximation strategy. We validate our approach on the Slakh dataset arXiv:1909.08494, demonstrating results in line with state of the art supervised approaches while requiring fewer resources with respect to other unsupervised methods.
State-of-the-art approaches for visually-guided audio source separation typically assume sources that have characteristic sounds, such as musical instruments. These approaches often ignore the visual context of these sound sources or avoid modeling object interactions that may be useful to better characterize the sources, especially when the same object class may produce varied sounds from distinct interactions. To address this challenging problem, we propose Audio Visual Scene Graph Segmenter (AVSGS), a novel deep learning model that embeds the visual structure of the scene as a graph and segments this graph into subgraphs, each subgraph being associated with a unique sound obtained by co-segmenting the audio spectrogram. At its core, AVSGS uses a recursive neural network that emits mutually-orthogonal sub-graph embeddings of the visual graph using multi-head attention. These embeddings are used for conditioning an audio encoder-decoder towards source separation. Our pipeline is trained end-to-end via a self-supervised task consisting of separating audio sources using the visual graph from artificially mixed sounds. In this paper, we also introduce an "in the wild'' video dataset for sound source separation that contains multiple non-musical sources, which we call Audio Separation in the Wild (ASIW). This dataset is adapted from the AudioCaps dataset, and provides a challenging, natural, and daily-life setting for source separation. Thorough experiments on the proposed ASIW and the standard MUSIC datasets demonstrate state-of-the-art sound separation performance of our method against recent prior approaches.
The audio source separation tasks, such as speech enhancement, speech separation, and music source separation, have achieved impressive performance in recent studies. The powerful modeling capabilities of deep neural networks give us hope for more challenging tasks. This paper launches a new multi-task audio source separation (MTASS) challenge to separate the speech, music, and noise signals from the monaural mixture. First, we introduce the details of this task and generate a dataset of mixtures containing speech, music, and background noises. Then, we propose an MTASS model in the complex domain to fully utilize the differences in spectral characteristics of the three audio signals. In detail, the proposed model follows a two-stage pipeline, which separates the three types of audio signals and then performs signal compensation separately. After comparing different training targets, the complex ratio mask is selected as a more suitable target for the MTASS. The experimental results also indicate that the residual signal compensation module helps to recover the signals further. The proposed model shows significant advantages in separation performance over several well-known separation models.
This paper introduces an alternative approach to sampling from autoregressive models. Autoregressive models are typically sampled sequentially, according to the transition dynamics defined by the model. Instead, we propose a sampling procedure that initializes a sequence with white noise and follows a Markov chain defined by Langevin dynamics on the global log-likelihood of the sequence. This approach parallelizes the sampling process and generalizes to conditional sampling. Using an autoregressive model as a Bayesian prior, we can steer the output of a generative model using a conditional likelihood or constraints. We apply these techniques to autoregressive models in the visual and audio domains, with competitive results for audio source separation, super-resolution, and inpainting.
We introduce the active audio-visual source separation problem, where an agent must move intelligently in order to better isolate the sounds coming from an object of interest in its environment. The agent hears multiple audio sources simultaneously (e.g., a person speaking down the hall in a noisy household) and it must use its eyes and ears to automatically separate out the sounds originating from a target object within a limited time budget. Towards this goal, we introduce a reinforcement learning approach that trains movement policies controlling the agent's camera and microphone placement over time, guided by the improvement in predicted audio separation quality. We demonstrate our approach in scenarios motivated by both augmented reality (system is already co-located with the target object) and mobile robotics (agent begins arbitrarily far from the target object). Using state-of-the-art realistic audio-visual simulations in 3D environments, we demonstrate our model's ability to find minimal movement sequences with maximal payoff for audio source separation. Project: http://vision.cs.utexas.edu/projects/move2hear.
Audio source separation is often used as preprocessing of various applications, and one of its ultimate goals is to construct a single versatile model capable of dealing with the varieties of audio signals. Since sampling frequency, one of the audio signal varieties, is usually application specific, the preceding audio source separation model should be able to deal with audio signals of all sampling frequencies specified in the target applications. However, conventional models based on deep neural networks (DNNs) are trained only at the sampling frequency specified by the training data, and there are no guarantees that they work with unseen sampling frequencies. In this paper, we propose a convolution layer capable of handling arbitrary sampling frequencies by a single DNN. Through music source separation experiments, we show that the introduction of the proposed layer enables a conventional audio source separation model to consistently work with even unseen sampling frequencies.
This dissertation proposes the study of multimodal learning in the context of musical signals. Throughout, we focus on the interaction between audio signals and text information. Among the many text sources related to music that can be used (e.g. reviews, metadata, or social network feedback), we concentrate on lyrics. The singing voice directly connects the audio signal and the text information in a unique way, combining melody and lyrics where a linguistic dimension complements the abstraction of musical instruments. Our study focuses on the audio and lyrics interaction for targeting source separation and informed content estimation.
We propose DiffQ a differentiable method for model compression for quantizing model parameters without gradient approximations (e.g., Straight Through Estimator). We suggest adding independent pseudo quantization noise to model parameters during training to approximate the effect of a quantization operator. DiffQ is differentiable both with respect to the unquantized weights and the number of bits used. Given a single hyper-parameter balancing between the quantized model size and accuracy, DiffQ optimizes the number of bits used per individual weight or groups of weights, in end-to-end training. We experimentally verify that our method is competitive with STE based quantization techniques on several benchmarks and architectures for image classification, language modeling, and audio source separation. For instance, on the ImageNet dataset, DiffQ compresses a 12 layers transformer-based model by more than a factor of 8, (lower than 4 bits precision per weight on average), with a loss of 0.3% in model accuracy. Code is available at github.com/facebookresearch/diffq.
Learning how to localize and separate individual object sounds in the audio channel of the video is a difficult task. Current state-of-the-art methods predict audio masks from artificially mixed spectrograms, known as Mix-and-Separate framework. We propose an audio-visual co-segmentation, where the network learns both what individual objects look and sound like, from videos labeled with only object labels. Unlike other recent visually-guided audio source separation frameworks, our architecture can be learned in an end-to-end manner and requires no additional supervision or bounding box proposals. Specifically, we introduce weakly-supervised object segmentation in the context of sound separation. We also formulate spectrogram mask prediction using a set of learned mask bases, which combine using coefficients conditioned on the output of object segmentation , a design that facilitates separation. Extensive experiments on the MUSIC dataset show that our proposed approach outperforms state-of-the-art methods on visually guided sound source separation and sound denoising.
Recent progress in audio source separation lead by deep learning has enabled many neural network models to provide robust solutions to this fundamental estimation problem. In this study, we provide a family of efficient neural network architectures for general purpose audio source separation while focusing on multiple computational aspects that hinder the application of neural networks in real-world scenarios. The backbone structure of this convolutional network is the SUccessive DOwnsampling and Resampling of Multi-Resolution Features (SuDoRM-RF) as well as their aggregation which is performed through simple one-dimensional convolutions. This mechanism enables our models to obtain high fidelity signal separation in a wide variety of settings where variable number of sources are present and with limited computational resources (e.g. floating point operations, memory footprint, number of parameters and latency). Our experiments show that SuDoRM-RF models perform comparably and even surpass several state-of-the-art benchmarks with significantly higher computational resource requirements. The causal variation of SuDoRM-RF is able to obtain competitive performance in real-time speech separation of around 10dB scale-invariant signal-to-distortion ratio improvement (SI-SDRi) while remaining up to 20 times faster than real-time on a laptop device.
Recently, significant progress has been made in audio source separation by the application of deep learning techniques. Current methods that combine both audio and visual information use 2D representations such as images to guide the separation process. However, in order to (re)-create acoustically correct scenes for 3D virtual/augmented reality applications from recordings of real music ensembles, detailed information about each sound source in the 3D environment is required. This demand, together with the proliferation of 3D visual acquisition systems like LiDAR or rgb-depth cameras, stimulates the creation of models that can guide the audio separation using 3D visual information. This paper proposes a multi-modal deep learning model to perform music source separation conditioned on 3D point clouds of music performance recordings. This model extracts visual features using 3D sparse convolutions, while audio features are extracted using dense convolutions. A fusion module combines the extracted features to finally perform the audio source separation. It is shown, that the presented model can distinguish the musical instruments from a single 3D point cloud frame, and perform source separation qualitatively similar to a reference case, where manually assigned instrument labels are provided.
In blind source separation of speech signals, the inherent imbalance in the source spectrum poses a challenge for methods that rely on single-source dominance for the estimation of the mixing matrix. We propose an algorithm based on the directional sparse filtering (DSF) framework that utilizes the Lehmer mean with learnable weights to adaptively account for source imbalance. Performance evaluation in multiple real acoustic environments show improvements in source separation compared to the baseline methods.
Augmented listening devices such as hearing aids often perform poorly in noisy and reverberant environments with many competing sound sources. Large distributed microphone arrays can improve performance, but data from remote microphones often cannot be used for delay-constrained real-time processing. We present a cooperative audio source separation and enhancement system that leverages wearable listening devices and other microphone arrays spread around a room. The full distributed array is used to separate sound sources and estimate their statistics. Each listening device uses these statistics to design real-time binaural audio enhancement filters using its own local microphones. The system is demonstrated experimentally using 10 speech sources and 160 microphones in a large, reverberant room.
In this paper, we address a multichannel audio source separation task and propose a new efficient method called independent deeply learned matrix analysis (IDLMA). IDLMA estimates the demixing matrix in a blind manner and updates the time-frequency structures of each source using a pretrained deep neural network (DNN). Also, we introduce a complex Student's t-distribution as a generalized source generative model including both complex Gaussian and Cauchy distributions. Experiments are conducted using music signals with a training dataset, and the results show the validity of the proposed method in terms of separation accuracy and computational cost.