arXiv subjects

Shoji Makino

Publications and source records attributed to Shoji Makino.

At least 19 recordsLinked to original sources

arXiv2026

Geometrically Constrained Decentralized Independent Vector Analysis for Distributed Microphone Arrays

This paper proposes a geometrically constrained decentralized independent vector analysis (GC-Dec-IVA) method for distributed microphone arrays. Recently proposed Dec-IVA method enables source separation by exchanging only power-related statistics to exploit cross-array information. However, this initial attempt often provides negligible improvement over applying IVA locally at each array, mainly due to the potential permutation inconsistency among arrays and the strong cross-array dependency implied by its source model. To address these limitations, we incorporate direction-of-arrival (DOA) information to derive GC-Dec-IVA, which mitigates permutation mismatch across arrays and enhances source alignment. Furthermore, a new source model is introduced to weaken cross-array dependency, improving robustness against permutation inconsistency in noisy environments. Experiments show the proposed method improves both the separation performance and cross-array permutation consistency.

eess.AS↗

arXiv2026

Neural Network-Based Time-Frequency-Bin-Wise Linear Combination of Beamformers for Underdetermined Target Source Extraction

Extracting a target source from underdetermined mixtures is challenging for beamforming approaches. Recently proposed time-frequency-bin-wise switching (TFS) and linear combination (TFLC) strategies mitigate this by combining multiple beamformers in each time-frequency (TF) bin and choosing combination weights that minimize the output power. However, making this decision independently for each TF bin can weaken temporal-spectral coherence, causing discontinuities and consequently degrading extraction performance. In this paper, we propose a novel neural network-based time-frequency-bin-wise linear combination (NN-TFLC) framework that constructs minimum power distortionless response (MPDR) beamformers without explicit noise covariance estimation. The network encodes the mixture and beamformer outputs, and predicts temporally and spectrally coherent linear combination weights via a cross-attention mechanism. On dual-microphone mixtures with multiple interferers, NN-TFLC-MPDR consistently outperforms TFS/TFLC-MPDR and achieves competitive performance with TFS/TFLC built on the minimum variance distortionless response (MVDR) beamformers that require noise priors.

eess.AS↗

arXiv2026

Entropy-Guided GRVQ for Ultra-Low Bitrate Neural Speech Codec

Neural audio codec (NAC) is essential for reconstructing high-quality speech signals and generating discrete representations for downstream speech language models. However, ensuring accurate semantic modeling while maintaining high-fidelity reconstruction under ultra-low bitrate constraints remains challenging. We propose an entropy-guided group residual vector quantization (EG-GRVQ) for an ultra-low bitrate neural speech codec, which retains a semantic branch for linguistic information and incorporates an entropy-guided grouping strategy in the acoustic branch. Assuming that channel activations follow approximately Gaussian statistics, the variance of each channel can serve as a principled proxy for its information content. Based on this assumption, we partition the encoder output such that each group carries an equal share of the total information. This balanced allocation improves codebook efficiency and reduces redundancy. Trained on LibriTTS and VCTK, our model shows improvements in perceptual quality and intelligibility metrics under ultra-low bitrate conditions, with a focus on codec-level fidelity for communication-oriented scenarios.

eess.AS↗

arXiv2026

Robust Online Overdetermined Independent Vector Analysis Based on Bilinear Decomposition

Online blind source separation is essential for both speech communication and human-machine interaction. Among existing approaches, overdetermined independent vector analysis (OverIVA) delivers strong performance by exploiting the statistical independence of source signals and the orthogonality between source and noise subspaces. However, when applied to large microphone arrays, the number of parameters grows rapidly, which can degrade online estimation accuracy. To overcome this challenge, we propose decomposing each long separation filter into a bilinear form of two shorter filters, thereby reducing the number of parameters. Because the two filters are closely coupled, we design an alternating iterative projection algorithm to update them in turn. Simulation results show that, with far fewer parameters, the proposed method achieves improved performance and robustness.

eess.AS↗

arXiv2025

Accelerated Convolutive Transfer Function-Based Multichannel NMF Using Iterative Source Steering

Among numerous blind source separation (BSS) methods, convolutive transfer function-based multichannel non-negative matrix factorization (CTF-MNMF) has demonstrated strong performance in highly reverberant environments by modeling multi-frame correlations of delayed source signals. However, its practical deployment is hindered by the high computational cost associated with the iterative projection (IP) update rule, which requires matrix inversion for each source. To address this issue, we propose an efficient variant of CTF-MNMF that integrates iterative source steering (ISS), a matrix inversion-free update rule for separation filters. Experimental results show that the proposed method achieves comparable or superior separation performance to the original CTF-MNMF, while significantly reducing the computational complexity.

cs.SD↗

arXiv2024

Low algorithmic delay implementation of convolutional beamformer for online joint source separation and dereverberation

Blind-audio-source-separation (BASS) techniques, particularly those with low latency, play an important role in a wide range of real-time systems, e.g., hearing aids, in-car hand-free voice communication, real-time human-machine interaction, etc. Most existing BASS algorithms are deduced to run on batch mode, and therefore large latency is unavoidable. Recently, some online algorithms were developed, which achieve separation on a frame-by-frame basis in the short-time-Fourier-transform (STFT) domain and the latency is significantly reduced as compared to those batch methods. However, the latency with these algorithms may still be too long for many real-time systems to bear. To further reduce latency while achieving good separation performance, we propose in this work to integrate a weighted prediction error (WPE) module into a non-causal sample-truncating-based independent vector analysis (NST-IVA). The resulting algorithm can maintain the algorithmic delay as NST-IVA if the delay with WPE is appropriately controlled while achieving significantly better performance, which is validated by simulations.

eess.AS↗

arXiv2024

Unrestricted Global Phase Bias-Aware Single-channel Speech Enhancement with Conformer-based Metric GAN

With the rapid development of neural networks in recent years, the ability of various networks to enhance the magnitude spectrum of noisy speech in the single-channel speech enhancement domain has become exceptionally outstanding. However, enhancing the phase spectrum using neural networks is often ineffective, which remains a challenging problem. In this paper, we found that the human ear cannot sensitively perceive the difference between a precise phase spectrum and a biased phase (BP) spectrum. Therefore, we propose an optimization method of phase reconstruction, allowing freedom on the global-phase bias instead of reconstructing the precise phase spectrum. We applied it to a Conformer-based Metric Generative Adversarial Networks (CMGAN) baseline model, which relaxes the existing constraints of precise phase and gives the neural network a broader learning space. Results show that this method achieves a new state-of-the-art performance without incurring additional computational overhead.

eess.AS↗

arXiv2023

A computationally efficient semi-blind source separation based approach for nonlinear echo cancellation based on an element-wise iterative source steering

While the semi-blind source separation-based acoustic echo cancellation (SBSS-AEC) has received much research attention due to its promising performance during double-talk compared to the traditional adaptive algorithms, it suffers from system latency and nonlinear distortions. To circumvent these drawbacks, the recently developed ideas on convolutive transfer function (CTF) approximation and nonlinear expansion have been used in the iterative projection (IP)-based semi-blind source separation (SBSS) algorithm. However, because of the introduction of CTF approximation and nonlinear expansion, this algorithm becomes computationally very expensive, which makes it difficult to implement in embedded systems. Thus, we attempt in this paper to improve this IP-based algorithm, thereby developing an element-wise iterative source steering (EISS) algorithm. In comparison with the IP-based SBSS algorithm, the proposed algorithm is computationally much more efficient, especially when the nonlinear expansion order is high and the length of the CTF filter is long. Meanwhile, its AEC performance is as good as that of IP-based SBSS.

eess.AS↗

arXiv2023

Neural network-based virtual microphone estimation with virtual microphone and beamformer-level multi-task loss

Array processing performance depends on the number of microphones available. Virtual microphone estimation (VME) has been proposed to increase the number of microphone signals artificially. Neural network-based VME (NN-VME) trains an NN with a VM-level loss to predict a signal at a microphone location that is available during training but not at inference. However, this training objective may not be optimal for a specific array processing back-end, such as beamforming. An alternative approach is to use a training objective considering the array-processing back-end, such as a loss on the beamformer output. This approach may generate signals optimal for beamforming but not physically grounded. To combine the advantages of both approaches, this paper proposes a multi-task loss for NN-VME that combines both VM-level and beamformer-level losses. We evaluate the proposed multi-task NN-VME on multi-talker underdetermined conditions and show that it achieves a 33.1 % relative WER improvement compared to using only real microphones and 10.8 % compared to using a prior NN-VME approach.

eess.AS↗

arXiv2022

FastMVAE2: On improving and accelerating the fast variational autoencoder-based source separation algorithm for determined mixtures

This paper proposes a new source model and training scheme to improve the accuracy and speed of the multichannel variational autoencoder (MVAE) method. The MVAE method is a recently proposed powerful multichannel source separation method. It consists of pretraining a source model represented by a conditional VAE (CVAE) and then estimating separation matrices along with other unknown parameters so that the log-likelihood is non-decreasing given an observed mixture signal. Although the MVAE method has been shown to provide high source separation performance, one drawback is the computational cost of the backpropagation steps in the separation-matrix estimation algorithm. To overcome this drawback, a method called "FastMVAE" was subsequently proposed, which uses an auxiliary classifier VAE (ACVAE) to train the source model. By using the classifier and encoder trained in this way, the optimal parameters of the source model can be inferred efficiently, albeit approximately, in each step of the algorithm. However, the generalization capability of the trained ACVAE source model was not satisfactory, which led to poor performance in situations with unseen data. To improve the generalization capability, this paper proposes a new model architecture (called the "ChimeraACVAE" model) and a training scheme based on knowledge distillation. The experimental results revealed that the proposed source model trained with the proposed loss function achieved better source separation performance with less computation time than FastMVAE. We also confirmed that our methods were able to separate 18 sources with a reasonably good accuracy.

cs.SD↗

arXiv2021

Speech Enhancement by Noise Self-Supervised Rank-Constrained Spatial Covariance Matrix Estimation via Independent Deeply Learned Matrix Analysis

Rank-constrained spatial covariance matrix estimation (RCSCME) is a method for the situation that the directional target speech and the diffuse noise are mixed. In conventional RCSCME, independent low-rank matrix analysis (ILRMA) is used as the preprocessing method. We propose RCSCME using independent deeply learned matrix analysis (IDLMA), which is a supervised extension of ILRMA. In this method, IDLMA requires deep neural networks (DNNs) to separate the target speech and the noise. We use Denoiser, which is a single-channel speech enhancement DNN, in IDLMA to estimate not only the target speech but also the noise. We also propose noise self-supervised RCSCME, in which we estimate the noise-only time intervals using the output of Denoiser and design the prior distribution of the noise spatial covariance matrix for RCSCME. We confirm that the proposed methods outperform the conventional methods under several noise conditions.

cs.SD↗

arXiv2019

Fast MVAE: Joint separation and classification of mixed sources based on multichannel variational autoencoder with auxiliary classifier

This paper proposes an alternative algorithm for multichannel variational autoencoder (MVAE), a recently proposed multichannel source separation approach. While MVAE is notable in its impressive source separation performance, the convergence-guaranteed optimization algorithm and that it allows us to estimate source-class labels simultaneously with source separation, there are still two major drawbacks, i.e., the high computational complexity and unsatisfactory source classification accuracy. To overcome these drawbacks, the proposed method employs an auxiliary classifier VAE, an information-theoretic extension of the conditional VAE, for learning the generative model of the source spectrograms. Furthermore, with the trained auxiliary classifier, we introduce a novel algorithm for the optimization that is able to not only reduce the computational time but also improve the source classification performance. We call the proposed method "fast MVAE (fMVAE)". Experimental evaluations revealed that fMVAE achieved comparative source separation performance to MVAE and about 80% source classification accuracy rate while it reduced about 93% computational time.

cs.LG↗

arXiv2018

Semi-blind source separation with multichannel variational autoencoder

This paper proposes a multichannel source separation technique called the multichannel variational autoencoder (MVAE) method, which uses a conditional VAE (CVAE) to model and estimate the power spectrograms of the sources in a mixture. By training the CVAE using the spectrograms of training examples with source-class labels, we can use the trained decoder distribution as a universal generative model capable of generating spectrograms conditioned on a specified class label. By treating the latent space variables and the class label as the unknown parameters of this generative model, we can develop a convergence-guaranteed semi-blind source separation algorithm that consists of iteratively estimating the power spectrograms of the underlying sources as well as the separation matrices. In experimental evaluations, our MVAE produced better separation performance than a baseline method.

stat.ML↗

arXiv2015

Chromatic and High-frequency cVEP-based BCI Paradigm

We present results of an approach to a code-modulated visual evoked potential (cVEP) based brain-computer interface (BCI) paradigm using four high-frequency flashing stimuli. To generate higher frequency stimulation compared to the state-of-the-art cVEP-based BCIs, we propose to use the light-emitting diodes (LEDs) driven from a small micro-controller board hardware generator designed by our team. The high-frequency and green-blue chromatic flashing stimuli are used in the study in order to minimize a danger of a photosensitive epilepsy (PSE). We compare the the green-blue chromatic cVEP-based BCI accuracies with the conventional white-black flicker based interface.

q-bio.NC↗

arXiv2015

Inter-stimulus Interval Study for the Tactile Point-pressure Brain-computer Interface

The paper presents a study of an inter-stimulus interval (ISI) influence on a tactile point-pressure stimulus-based brain-computer interface's (tpBCI) classification accuracy. A novel tactile pressure generating tpBCI stimulator is also discussed, which is based on a three-by-three pins' matrix prototype. The six pin-linear patterns are presented to the user's palm during the online tpBCI experiments in an oddball style paradigm allowing for "the aha-responses" elucidation, within the event related potential (ERP). A subsequent classification accuracies' comparison is discussed based on two ISI settings in an online tpBCI application. A research hypothesis of classification accuracies' non-significant differences with various ISIs is confirmed based on the two settings of 120 ms and 300 ms, as well as with various numbers of ERP response averaging scenarios.

q-bio.NC↗

arXiv2015

Head-related Impulse Response Cues for Spatial Auditory Brain-computer Interface

This study provides a comprehensive test of a head-related impulse response (HRIR) cues for a spatial auditory brain-computer interface (saBCI) speller paradigm. We present a comparison with the conventional virtual sound headphone-based spatial auditory modality. We propose and optimize the three types of sound spatialization settings using a variable elevation in order to evaluate the HRIR efficacy for the saBCI. Three experienced and seven naive BCI users participated in the three experimental setups based on ten presented Japanese syllables. The obtained EEG auditory evoked potentials (AEP) resulted with encouragingly good and stable P300 responses in online BCI experiments. Our case study indicated that users could perceive elevation in the saBCI experiments generated using the HRIR measured from a general head model. The saBCI accuracy and information transfer rate (ITR) scores have been improved comparing to the classical horizontal plane-based virtual spatial sound reproduction modality, as far as the healthy users in the current pilot study are concerned.

q-bio.NC↗

arXiv2015

Spatial Auditory Brain-computer Interface using Head Related Impulse Response

This study reports on a head related impulse response (HRIR) application to an auditory spatial brain-computer interface (BCI) speller paradigm. Six experienced and five BCI-naive users participated in an experimental spelling set up based on five Japanese vowels. Obtained auditory evoked potentials resulted with encouragingly good and stable P300-responses in online BCI experiments. Our case study indicated that the headphone reproduced auditory (HRIR- based) spatial sound paradigm could be a viable alternative to the established multi-loudspeaker surround sound BCI-speller applications, as far as healthy pilot study users are concerned.

q-bio.NC↗

arXiv2014

Spatial Tactile Brain-Computer Interface Paradigm Applying Vibration Stimuli to Large Areas of User's Back

We aim at an augmentation of communication abilities of amyotrophic lateral sclerosis (ALS) patients by creating a brain-computer interface (BCI) which can control a computer or other device by using only brain activity. As a method, we use a stimulus-driven BCI based on vibration stimuli delivered via a gaming pad to the user's back. We identify P300 responses from brain activity data in response to the vibration stimuli. The user's intentions are classified according to the P300 responses recorded in the EEG. From the results of the psychophysical and online BCI experiments, we are able to classify the P300 responses very accurately, which proves the effectiveness of the proposed method.

q-bio.NC↗