Neural Fast Full-Rank Spatial Covariance Analysis for Blind Source Separation

This paper describes an efficient unsupervised learning method for a neural source separation model that utilizes a probabilistic generative model of observed multichannel mixtures proposed for blind source separation (BSS). For this purpose, amortized variational inference (AVI) has been used for directly solving the inverse problem of BSS with full-rank spatial covariance analysis (FCA). Although this unsupervised technique called neural FCA is in principle free from the domain mismatch problem, it is computationally demanding due to the full rankness of the spatial model in exchange for robustness against relatively short reverberations. To reduce the model complexity without sacrificing performance, we propose neural FastFCA based on the jointly-diagonalizable yet full-rank spatial model. Our neural separation model introduced for AVI alternately performs neural network blocks and single steps of an efficient iterative algorithm called iterative source steering. This alternating architecture enables the separation model to quickly separate the mixture spectrogram by leveraging both the deep neural network and the multichannel optimization algorithm. The training objective with AVI is derived to maximize the marginalized likelihood of the observed mixtures. The experiment using mixture signals of two to four sound sources shows that neural FastFCA outperforms conventional BSS methods and reduces the computational time to about 2% of that for the neural FCA.

Neural Steerer: Novel Steering Vector Synthesis with a Causal Neural Field over Frequency and Source Positions

Neural fields have successfully been used in many research fields for their native ability to estimate a continuous function from a finite number of observations. In audio processing, this technique has been applied to acoustic and head-related transfer function interpolation. However, most of the existing methods estimate the real-valued magnitude function over a predefined discrete set of frequencies. In this study, we propose a novel approach for steering vector interpolation that regards frequencies as continuous input variables. Moreover, we propose a novel unsupervised regularization term enforcing the estimated filters to be causal. The experiment using real steering vectors show that the proposed frequency resolution-free method outperformed the existing methods operating over discrete set of frequencies.

DNN-Free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online FastMNMF

This paper describes a practical dual-process speech enhancement system that adapts environment-sensitive frame-online beamforming (front-end) with help from environment-free block-online source separation (back-end). To use minimum variance distortionless response (MVDR) beamforming, one may train a deep neural network (DNN) that estimates time-frequency masks used for computing the covariance matrices of sources (speech and noise). Backpropagation-based run-time adaptation of the DNN was proposed for dealing with the mismatched training-test conditions. Instead, one may try to directly estimate the source covariance matrices with a state-of-the-art blind source separation method called fast multichannel non-negative matrix factorization (FastMNMF). In practice, however, neither the DNN nor the FastMNMF can be updated in a frame-online manner due to its computationally-expensive iterative nature. Our DNN-free system leverages the posteriors of the latest source spectrograms given by block-online FastMNMF to derive the current source covariance matrices for frame-online beamforming. The evaluation shows that our frame-online system can quickly respond to scene changes caused by interfering speaker movements and outperformed an existing block-online system with DNN-based beamforming by 5.0 points in terms of the word error rate.

Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments

This paper describes the practical response- and performance-aware development of online speech enhancement for an augmented reality (AR) headset that helps a user understand conversations made in real noisy echoic environments (e.g., cocktail party). One may use a state-of-the-art blind source separation method called fast multichannel nonnegative matrix factorization (FastMNMF) that works well in various environments thanks to its unsupervised nature. Its heavy computational cost, however, prevents its application to real-time processing. In contrast, a supervised beamforming method that uses a deep neural network (DNN) for estimating spatial information of speech and noise readily fits real-time processing, but suffers from drastic performance degradation in mismatched conditions. Given such complementary characteristics, we propose a dual-process robust online speech enhancement method based on DNN-based beamforming with FastMNMF-guided adaptation. FastMNMF (back end) is performed in a mini-batch style and the noisy and enhanced speech pairs are used together with the original parallel training data for updating the direction-aware DNN (front end) with backpropagation at a computationally-allowable interval. This method is used with a blind dereverberation method called weighted prediction error (WPE) for transcribing the noisy reverberant speech of a speaker, which can be detected from video or selected by a user's hand gesture or eye gaze, in a streaming manner and spatially showing the transcriptions with an AR technique. Our experiment showed that the word error rate was improved by more than 10 points with the run-time adaptation using only twelve minutes of observation.

Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments

This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments. A major approach that has actively been studied in simulated environments is to sequentially perform speech enhancement and automatic speech recognition (ASR) based on deep neural networks (DNNs) trained in a supervised manner. In our task, however, such a pretrained system fails to work due to the mismatch between the training and test conditions and the head movements of the user. To enhance only the utterances of a target speaker, we use beamforming based on a DNN-based speech mask estimator that can adaptively extract the speech components corresponding to a head-relative particular direction. We propose a semi-supervised adaptation method that jointly updates the mask estimator and the ASR model at run-time using clean speech signals with ground-truth transcriptions and noisy speech signals with highly-confident estimated transcriptions. Comparative experiments using the state-of-the-art distant speech recognition system show that the proposed method significantly improves the ASR performance.

Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation

This paper describes heavy-tailed extensions of a state-of-the-art versatile blind source separation method called fast multichannel nonnegative matrix factorization (FastMNMF) from a unified point of view. The common way of deriving such an extension is to replace the multivariate complex Gaussian distribution in the likelihood function with its heavy-tailed generalization, e.g., the multivariate complex Student's t and leptokurtic generalized Gaussian distributions, and tailor-make the corresponding parameter optimization algorithm. Using a wider class of heavy-tailed distributions called a Gaussian scale mixture (GSM), i.e., a mixture of Gaussian distributions whose variances are perturbed by positive random scalars called impulse variables, we propose GSM-FastMNMF and develop an expectationmaximization algorithm that works even when the probability density function of the impulse variables have no analytical expressions. We show that existing heavy-tailed FastMNMF extensions are instances of GSM-FastMNMF and derive a new instance based on the generalized hyperbolic distribution that include the normal-inverse Gaussian, Student's t, and Gaussian distributions as the special cases. Our experiments show that the normalinverse Gaussian FastMNMF outperforms the state-of-the-art FastMNMF extensions and ILRMA model in speech enhancement and separation in terms of the signal-to-distortion ratio.

Global Structure-Aware Drum Transcription Based on Self-Attention Mechanisms

This paper describes an automatic drum transcription (ADT) method that directly estimates a tatum-level drum score from a music signal, in contrast to most conventional ADT methods that estimate the frame-level onset probabilities of drums. To estimate a tatum-level score, we propose a deep transcription model that consists of a frame-level encoder for extracting the latent features from a music signal and a tatum-level decoder for estimating a drum score from the latent features pooled at the tatum level. To capture the global repetitive structure of drum scores, which is difficult to learn with a recurrent neural network (RNN), we introduce a self-attention mechanism with tatum-synchronous positional encoding into the decoder. To mitigate the difficulty of training the self-attention-based model from an insufficient amount of paired data and improve the musical naturalness of the estimated scores, we propose a regularized training method that uses a global structure-aware masked language (score) model with a self-attention mechanism pretrained from an extensive collection of drum scores. Experimental results showed that the proposed regularized model outperformed the conventional RNN-based model in terms of the tatum-level error rate and the frame-level F-measure, even when only a limited amount of paired data was available so that the non-regularized model underperformed the RNN-based model.

Tatum-Level Drum Transcription Based on a Convolutional Recurrent Neural Network with Language Model-Based Regularized Training

This paper describes a neural drum transcription method that detects from music signals the onset times of drums at the $\textit{tatum}$ level, where tatum times are assumed to be estimated in advance. In conventional studies on drum transcription, deep neural networks (DNNs) have often been used to take a music spectrogram as input and estimate the onset times of drums at the $\textit{frame}$ level. The major problem with such frame-to-frame DNNs, however, is that the estimated onset times do not often conform with the typical tatum-level patterns appearing in symbolic drum scores because the long-term musically meaningful structures of those patterns are difficult to learn at the frame level. To solve this problem, we propose a regularized training method for a frame-to-tatum DNN. In the proposed method, a tatum-level probabilistic language model (gated recurrent unit (GRU) network or repetition-aware bi-gram model) is trained from an extensive collection of drum scores. Given that the musical naturalness of tatum-level onset times can be evaluated by the language model, the frame-to-tatum DNN is trained with a regularizer based on the pretrained language model. The experimental results demonstrate the effectiveness of the proposed regularized training method.

The MIDI Degradation Toolkit: Symbolic Music Augmentation and Correction

In this paper, we introduce the MIDI Degradation Toolkit (MDTK), containing functions which take as input a musical excerpt (a set of notes with pitch, onset time, and duration), and return a "degraded" version of that excerpt with some error (or errors) introduced. Using the toolkit, we create the Altered and Corrupted MIDI Excerpts dataset version 1.0 (ACME v1.0), and propose four tasks of increasing difficulty to detect, classify, locate, and correct the degradations. We hypothesize that models trained for these tasks can be useful in (for example) improving automatic music transcription performance if applied as a post-processing step. To that end, MDTK includes a script that measures the distribution of different types of errors in a transcription, and creates a degraded dataset with similar properties. MDTK's degradations can also be applied dynamically to a dataset during training (with or without the above script), generating novel degraded excerpts each epoch. MDTK could also be used to test the robustness of any system designed to take MIDI (or similar) data as input (e.g. systems designed for voice separation, metrical alignment, or chord detection) to such transcription errors or otherwise noisy data. The toolkit and dataset are both publicly available online, and we encourage contribution and feedback from the community.

Semi-supervised Neural Chord Estimation Based on a Variational Autoencoder with Discrete Labels and Continuous Textures of Chords

This paper describes a statistically-principled semi-supervised method of automatic chord estimation (ACE) that can make effective use of any music signals regardless of the availability of chord annotations. The typical approach to ACE is to train a deep classification model (neural chord estimator) in a supervised manner by using only a limited amount of annotated music signals. In this discriminative approach, prior knowledge about chord label sequences (characteristics of model output) has scarcely been taken into account. In contract, we propose a unified generative and discriminative approach in the framework of amortized variational inference. More specifically, we formulate a deep generative model that represents the complex generative process of chroma vectors (observed variables) from the discrete labels and continuous textures of chords (latent variables). Chord labels and textures are assumed to follow a Markov model favoring self-transitions and a standard Gaussian distribution, respectively. Given chroma vectors as observed data, the posterior distributions of latent chord labels and textures are computed approximately by using deep classification and recognition models, respectively. These three models are combined to form a variational autoencoder and trained jointly in a semi-supervised manner. The experimental results show that the performance of the classification model can be improved by additionally using non-annotated music signals and/or by regularizing the classification model with the Markov model of chord labels and the generative model of chroma vectors even in the fully-supervised condition.