Justinian Rosca

First stereo audio source separation evaluation campaign: data, algorithms and results

This article provides an overview of the first stereo audio source separation evaluation campaign, organized by the authors. Fifteen underdetermined stereo source separation algorithms have been applied to various audio data, including instantaneous, convolutive and real mixtures of speech or music sources. The data and the algorithms are presented and the estimated source signals are compared to reference signals using several objective performance criteria.

CARS: Context-Aware Rate Selection for vehicular networks

Traffic querying, road sensing and mobile content delivery are emerging application domains for vehicular networks whose performance depends on the throughput these networks can sustain. Rate adaptation is one of the key mechanisms at the link layer that determine this performance. Rate adaptation in vehicular networks faces the following key challenges: (1) due to the rapid variations of the link quality caused by fading and mobility at vehicular speeds, the transmission rate must adapt fast in order to be effective, (2) during infrequent and bursty transmission, the rate adaptation scheme must be able to estimate the link quality with few or no packets transmitted in the estimation window, (3) the rate adaptation scheme must distinguish losses due to environment from those due to hidden-station induced collision. Our extensive outdoor experiments show that the existing rate adaptation schemes for 802.11 wireless networks under utilize the link capacity in vehicular environments. In this paper, we design, implement and evaluate CARS, a novel context-aware rate selection algorithm that makes use of context information (e.g. vehicle speed and distance from neighbor) to systematically address the above challenges, while maximizing the link throughput. Our experimental evaluation in real outdoor vehicular environments with different mobility scenarios shows that CARS adapts to changing link conditions at high vehicular speeds faster than existing rate-adaptation algorithms. Our scheme achieves significantly higher throughput, up to 79%, in all the tested scenarios, and is robust to packet loss due to collisions, improving the throughput by up to 256% in the presence of hidden stations.

Assessing communications technology options for smart grid applications

Utilities are at a crossroads in addressing challenges to architect communication networks that can support a robust blend of smart grid applications while simultaneously meeting stringent financial and regulatory objectives. This paper discusses challenges in understanding the communication network choices when supporting applications such as Distribution Automation, Advanced Metering, Automated Demand Response and Electric Vehicle Charging. We also introduce the unique capabilities of a tool designed to evaluate different communications technology choices under specific application, network, topology, and geographical constraints.

Microphone array speech enhancement by Bayesian estimation of spectral amplitude and phase

Microphone arrays provide new opportunities for noise reduction and speech enhancement. This paper presents a novel decomposition of the estimation problems for short-time spectral amplitude (STSA), log STSA, and phase in the Bayesian estimation framework. The decomposition is based on the notion of sufficient statistics for the microphone array case. It nicely generalizes the wellknown single-channel Ephraim-Malah estimators (1984, 1985) to the microphone array case. We also compare noise reduction obtained in the single channel with the two- and four-channel cases on real data.

Real-time audio source separation by delay and attenuation compensation in the time domain

There is increased interest in using microphone arrays in a variety of audio source separation and consequently speech processing applications. In particular, small arrays of two to four microphones are presently under focus in the research literature, especially with regard to real-time source separation and speech enhancement capability. In this paper we focus on a real-time implementation of the delay and attenuation compensation (DAC) algorithm. Although the algorithm is designed for anechoic environments, its complexity and performance on real data represent a basis for designing more complex approaches to deal with reverberant environments. We highlight real-time issues and analyze the algorithm’s real-time performance on a database of more than 1000 mixtures of real voice recordings ranging from an anechoic to a strongly echoic office with reverberation time of 500 msec.

Generalized sparse signal mixing model and application to noisy blind source separation

Sparse constraints on signal decompositions are justified by typical sensor data used in a variety of signal processing fields such as acoustics, medical imaging, or wireless, but moreover can lead to more effective algorithms. The specific sparseness assumption used in this work is that the maximum number of statistically independent sources active at any time and frequency point in a mixture of signals is small. This is shown to result from an assumption of sparseness of the sources themselves, and allows us to solve the maximum likelihood formulation of the noninstantaneous acoustic mixing source estimation problem. We consider an additive noise mixing model with an arbitrary number of sensors and possibly more sources than sensors, when sources satisfy the sparseness assumption above. The solution obtained is applicable to an arbitrary number of microphones and sources, but works best when the number of sources simultaneously active at any time frequency point is a small fraction of the total number of sources.

Speech Noise Estimation using Enhanced Minima Controlled Recursive Averaging

Accurate noise power spectrum estimation in a noisy speech signal is a key challenge problem in speech enhancement. One state-of-the-art approach is the minima controlled recursive averaging (MCRA). This paper presents an enhanced MCRA algorithm (EMCRA), which demonstrates less speech signal leakage and faster response time to follow abrupt changes in the noise power spectrum. Experiments using real speech and noise recordings have validated the superiority of the proposed enhancements. EMCRA shows improvements both in intuitive subjective listening and objective quality measures in terms of higher output SNR and lower output distortion scores.

Multi-channel psychoacoustically motivated speech enhancement

Multichannel techniques offer advantages in noise reduction and overall output signal quality when compared to the well studied mono approaches. In this paper we present an original multichannel psychoacoustically motivates noise reduction algorithm that naturally extends the single channel psychoacoustic masking filter previously studied in the literature [S. Gustafsson et al., 1999]. The optimality criterion is designed to simultaneously satisfy the psychoacoustic masking principle and minimize the signal total distortion. In experiments on real data recorded in a noisy car environment, we show the enhanced performance of the two-channel solution in terms of artifacts and overall tradeoff between artifacts and amount of noise removed as given by word recognition rates.

Enhanced VQ-based algorithms for speech independent speaker identification

Weighted distance measure and discriminative training are two different directions to enhance VQ-based solutions for speaker identification. In the first direction, the partition normalized distance measure successfully used normalized feature components to account for varying importance of the LPC coefficients. In the second direction, the group vector quantization speeded up discriminative training by randomly selecting a group of vectors as a training unit in each learning step. This paper introduces an alternative, called heuristic weighted distance, to linearly lift up higher order MFCC feature vector components. Then two new algorithms are proposed to combine the heuristic weighted distance and the partition normalized distance measure with the group vector quantization to take full advantage of both directions. Testing on the TIMIT and NTIMIT corpora showed that the proposed methods are superior to current VQ-based solutions, and are in a comparable range to the Gaussian Mixture Model using the Wavelet or MFCC features.

Airtime Fair Distributed Cross-Layer Congestion Control for Real-Time Video Over WLAN

We propose a distributed cross-layer congestion control algorithm that provides enhanced quality of service QoS and reliable operation for real-time uplink video over WiFi applications. Such applications are characterized by many wireless devices transmitting video at various PHY rates over a relatively congested channel. Unfortunately, todays off-the-shelf 802.11 equipment can be easily demonstrated to suffer catastrophic failure when subject to these conditions-let alone provide acceptable perceptual quality to the user. We show that in order to remedy these issues, it is preferable to apply airtime fairness with a cross-layer approach. The idea is to use a fast frame-by-frame control loop in the carrier sense multiple access/collision avoidance (CSMA/CA)-based medium access control (MAC) layer while simultaneously exploiting the powerful control loop gain attainable by performing source-rate adaptation in the application layer. We support the proposed algorithm through both simulation and experimentation with various channel and PHY rate scenarios.