24 accepted papers
Signal reconstruction from its mel-spectrogram is known as mel-spectrogram inversion and has many applications, including speech and foley sound synthesis. In this paper, we propose a mel-spectrogram inversion method based on a rigorous optimization algorithm. To reconstruct a time-domain signal wit…
In this paper, we investigate the effectiveness of spatial features for acoustic scene classification (ASC) with distributed microphones. Assuming that multiple subarrays, each containing multiple micro-phones, are distributed and synchronized, we consider two types of generalized cross-correlation…
Element selection techniques for high-dimensional features have various applications in machine learning. In general, the problem of element selection is typically solved by greedy methods or convex relaxation methods. However, these algorithms are applicable to only a specific class of optimization…
We address the problem of separating moving sources using online independent vector analysis (IVA). To solve this problem, researchers have extended the iterative projection (IP) and iterative source steering (ISS) algorithms developed for batch auxiliary-function-based IVA (AuxIVA) to online scenar…
In this work we detail our submission to the Clarity ICASSP 2023 grand challenge, in which participants have to develop a strong target speech enhancement system for hearing-aid (HA) devices in noisy-reverberant environments. Our system builds on our previous submission at the Second Clarity Enhance…
In the present study, we quantify entrainment characteristics of conversation with the aim of automatic assessment of the severity of autism spectrum disorder (ASD). We focus on pairs of utterances immediately before and after turn-takings, which have prosodic/acoustic similarities.The clinical seve…
Linear dimensionality reduction of signals observed by a sensor array is often useful in balancing the accuracy and speed of post-stage processing, especially in real-time systems with limited computational resources. However, for multichannel time-series signals having time-invariant intertemporal…
We propose a new algorithm for joint dereverberation and blind source separation (DR-BSS). Our work builds upon the IRLMA-T framework that applies a unified filter combining dereverberation and separation. One drawback of this framework is that it requires several matrix inversions, an operation inh…
In this paper, we present a novel framework of beamforming robust for a microphone array rotation. In most array signal processing methods, the time-invariant transfer system from a source to a microphone is assumed for calculating a spatial filter. This assumption makes it difficult to use the micr…
We propose fast independent vector extraction (FIVE), a new algorithm that blindly extracts a single non-Gaussian source from a Gaussian background. The algorithm iteratively computes beam-forming weights maximizing the signal-to-interference-and-noise ratio for an approximate noise covariance matri…
We propose a new algorithm for the blind source separation of acoustic sources. This algorithm is an alternative to the popular auxiliary function based independent vector analysis using iterative projection (AuxIVA-IP). It optimizes the same cost function, but instead of alternate updates of the ro…
In this paper, we propose a method of estimating the sampling frequency mismatch among asynchronous recording devices, even when the sources sometimes move. For a spatially stationary source, there is a method of estimating the sampling frequency mismatch, which appears in the drift of the time diff…
We propose a blind source separation algorithm that jointly exploits measurements by a conventional microphone array and an ad hoc array of low-rate sound power sensors called blinkies. While providing less information than microphones, blinkies circumvent some difficulties of microphone arrays in t…
In this paper, we present a speech enhancement method using two microphones in underdetermined situations. Time-frequency (TF) binary masking is a conventional method of enhancing speech in underdetermined situations by appropriately multiplying each TF component by zero or one. Extending this metho…
Hyperspectral reconstruction from RGB imaging has recently achieved significant progress via sparse coding and deep learning. However, a largely ignored fact is that existing RGB cameras are tuned to mimic human richromatic perception, thus their spectral responses are not necessarily optimal for h…
This paper addresses a front-end system for speech recognition of spontaneous conversational speech signals that are recorded with asynchronous distributed microphones such as smartphones. In our previous work, we proposed combining blind synchronization and a state-of-the-art microphone array speec…
In this paper, we propose a new blind source separation (BSS) method based on independent low-rank matrix analysis (ILRMA) with novel sparse regularization. ILRMA is a recently proposed BSS algorithm that simultaneously estimates a demixing matrix and source spectrogram models based on nonnegative m…
In this paper, we present a low-latency scheme for real-time blind source separation (BSS) based on online auxiliary-function-based independent vector analysis (AuxIVA). In many real-time audio applications, especially hearing aids, low latency is highly desirable. Conventional frequency-domain BSS…
This study is an experimental validation of a new closed-form method for automatic array position calibration, based on time of arrival (TOA) measurements between sources and sensors. An experiment with a large array composed of 121 microphones and a dozen of sources has been set up. We first show t…
We propose a novel method for analyzing acoustic scenes that can sophisticatedly estimate acoustic scenes from an acoustic event sequence with intermittent missing events. On the basis of the idea that acoustic events are temporally correlated, we model the transition of acoustic events using a hidd…
In this paper, an extension of independent vector analysis (IVA), model-based IVA, is proposed for multichannel source separation. For obtaining better source models, we introduce a single-channel source separation method, and utilize the outputs as source variances in time-frequency-variant Gaussia…
This paper proposes a new efficient multichannel nonnegative matrix factorization (NMF) method. Recently, multichannel NMF (MNMF) has been proposed as a means of solving the blind source separation problem. This method estimates a mixing system of sources and attempts to separate them in a blind fas…
Deep neural networks (DNN) are typically optimized with stochastic gradient descent (SGD) using a fixed learning rate or an adaptive learning rate approach (ADAGRAD). In this paper, we introduce a new learning rule for neural networks that is based on an auxiliary function technique without paramete…
In this paper, we present a new method to find solutions to the time difference of arrival (TDOA)-based source and sensor localization problem. This paper is a continuation of [1], in which sources and sensors are localized on the basis of time of arrival (TOA) measurements. Generally, the TOA is kn…