WEVOICE, Inc.

Bridgewater, NJ, United States

WEVOICE, Inc.

Bridgewater, NJ, United States
SEARCH FILTERS
Time filter
Source Type

Benesty J.,University of Québec | Chen J.,Northwestern Polytechnical University | Huang Y.,WEVOICE, Inc. | Gaensler T.,Mh Acoustics LLC
Journal of the Acoustical Society of America | Year: 2012

This paper addresses the problem of noise reduction in the time domain where the clean speech sample at every time instant is estimated by filtering a vector of the noisy speech signal. Such a clean speech estimate consists of both the filtered speech and residual noise (filtered noise) as the noisy vector is the sum of the clean speech and noise vectors. Traditionally, the filtered speech is treated as the desired signal after noise reduction. This paper proposes to decompose the clean speech vector into two orthogonal components: one is correlated and the other is uncorrelated with the current clean speech sample. While the correlated component helps estimate the clean speech, it is shown that the uncorrelated component interferes with the estimation, just as the additive noise. Based on this orthogonal decomposition, the paper presents a way to define the error signal and cost functions and addresses the issue of how to design different optimal noise reduction filters by optimizing these cost functions. Specifically, it discusses how to design the maximum SNR filter, the Wiener filter, the minimum variance distortionless response (MVDR) filter, the tradeoff filter, and the linearly constrained minimum variance (LCMV) filter. It demonstrates that the maximum SNR, Wiener, MVDR, and tradeoff filters are identical up to a scaling factor. It also shows from the orthogonal decomposition that many performance measures can be defined, which seem to be more appropriate than the traditional ones for the evaluation of the noise reduction filters. © 2012 Acoustical Society of America.


Benesty J.,University of Québec | Huang Y.,WEVOICE, Inc.
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | Year: 2011

Most existing approaches for single-channel noise reduction in the frequency domain via the short-time Fourier transform (STFT) assume that consecutive time-frames are uncorrelated with each other. As a result, algorithms based on this assumption do not, obviously, take the interframe correlation into account. In this paper, we propose a framework that considers this interframe correlation. An important consequence in including this useful information, is that now it is possible to derive a (single-channel) minimum variance distortionless response (MVDR) filter for noise reduction. The experimental study shows impressive results. © 2011 IEEE.


Benesty J.,University of Quebec at Montréal | Chen J.,WEVOICE, Inc. | Huang Y.,WEVOICE, Inc.
IEEE Signal Processing Letters | Year: 2010

Traditionally in the single-channel noise-reduction problem, speech distortion is inevitable since the desired signal is also filtered while filtering the noise. In fact, the more the noise is reduced, the more the speech distortion is added into the desired signal, as proved in the literature. So, if we require no speech distortion, we either end up with no noise reduction at all or have to use multiple sensors. In this paper, we attempt to apply the widely linear (WL) estimation theory to noise reduction. Unlike the traditional approaches that only filter the short-time Fourier transform (STFT) of the noisy signal, the method developed in this paper applies the noise-reduction filter to both the STFT of the noisy signal and its conjugate. With the constraint of no speech distortion, a WL distortionless filter is derived. We show that this new optimal filter can fully take advantage of the noncircularity property of speech signals to achieve up to 3-dB signal-to-noise-ratio (SNR) improvement without introducing any speech distortion, which can only be obtained with the traditional approaches if two or more microphones are used. © 2010 IEEE.


Benesty J.,University of Quebec at Montréal | Chen J.,Northwestern Polytechnical University | Huang Y.,WEVOICE, Inc.
IEEE Transactions on Audio, Speech and Language Processing | Year: 2011

Binaural noise reduction with a stereophonic (or simply stereo) setup has become a very important problem as stereo sound systems and devices are being more and more deployed in modern voice communications. This problem is very challenging since it requires not only the reduction of the noise at the stereo inputs, but also the preservation of the spatial information embodied in the two channels so that after noise reduction the listener can still localize the sound source from the binaural outputs. As a result, simply applying a traditional single-channel noise reduction technique to each channel individually may not work as the spatial effects may be destroyed. In this paper, we present a new formulation of the binaural noise reduction problem in stereo systems. We first form a complex signal from the stereo inputs with one channel being its real part and the other being its imaginary part. By doing so, the binaural noise reduction problem can be processed by a single-channel widely linear filter. The widely linear estimation theory is then used to derive optimal noise reduction filters that can fully take advantage of the noncircularity of the complex speech signal to achieve noise reduction while preserving the desired signal (speech) and spatial information. With this new formulation, the Wiener, minimum variance distortionless response (MVDR), maximum signal-to-noise ratio (SNR), and tradeoff filters are derived. Experiments are provided to justify the effectiveness of these filters. © 2011 IEEE.


Benesty J.,University of Quebec at Montréal | Souden M.,University of Quebec at Montréal | Huang Y.A.,WEVOICE, Inc.
IEEE Transactions on Audio, Speech and Language Processing | Year: 2012

In this correspondence, we study the performance of differential microphone arrays (DMAs) in terms of noise reduction, speech distortion, and signal-to-noise ratio (SNR) gain. We also investigate their beampatterns and array gains. We start by establishing the expressions of these performance measures involving general derivatives of the channel transfer functions. Afterwards, we specify our results in the case of anechoic near-field and far-field propagation models. © 2011 IEEE.


Huang Y.A.,WEVOICE, Inc. | Benesty J.,University of Quebec at Montréal
IEEE Transactions on Audio, Speech and Language Processing | Year: 2012

This paper focuses on the class of single-channel noise reduction methods that are performed in the frequency domain via the short-time Fourier transform (STFT). The simplicity and relative effectiveness of this class of approaches make them the dominant choice in practical systems. Over the past years, many popular algorithms have been proposed. These algorithms, no matter how they are developed, have one feature in common: the solution is eventually formulated as a gain function applied to the STFT of the noisy signal only in the current frame, implying that the interframe correlation is ignored. This assumption is not accurate for speech enhancement since speech is a highly self-correlated signal. In this paper, by taking the interframe correlation into account, a new linear model for speech spectral estimation and some optimal filters are proposed. They include the multi-frame Wiener and minimum variance distortionless response (MVDR) filters. With these filters, both the narrowband and fullband signal-to-noise ratios (SNRs) can be improved. Furthermore, with the MVDR filter, speech distortion at the output can be zero. Simulations present promising results in support of the claimed merits obtained by theoretical analysis. © 2011 IEEE.


Grant
Agency: National Aeronautics and Space Administration | Branch: | Program: SBIR | Phase: Phase II | Award Amount: 600.00K | Year: 2010

Astronauts suffer from poor dexterity of their hands due to the clumsy spacesuit gloves during Extravehicular Activity (EVA) operations and NASA has had a widely recognized but unmet need for novel human machine interface technologies to facilitate data entry, communications, and robots or intelligent systems control. The objective of this research project is to develop a speech human interface that can offer both crewmember usability and system operational efficiency. But loud noise and strong reverberation inside spacesuits make automatic speech recognition (ASR) for such an interface a very challenging problem. In Phase I, the feasibility of using WeVoice proprietary microphone array signal processing and robust ASR technologies was validated. In particular, it was found that novel multichannel noise reduction produces larger gain in SNR than conventional beamforming but the latter is more preferable as far as ASR is concerned. In addition, it was confirmed that the model adaptation algorithm can make an ASR system more robust inside spacesuits. An arithmetic complexity model for ASR was developed. It can direct the decision as to whether a specified speech interface is sufficiently efficient to be possibly implemented with a wearable system. Phase II will analyze and minimize the scientific and engineering uncertainties identified during Phase I. Furthermore, a voice command interface for future generations of a suit's processing system is proposed to be developed on DSP chips. The system should be ready for testing and use by NASA suited crewmembers at the end of Phase II.


Grant
Agency: National Aeronautics and Space Administration | Branch: | Program: SBIR | Phase: Phase I | Award Amount: 97.06K | Year: 2011

Acoustic survey is now performed using hand-held devices once every two months on the international space station (ISS). It takes quite a lot of precious crew time and the sporadic monitoring program is not adequate.This Phase I proposal is concerned with developing an automated sound level and noise exposure monitoring system running on a ZigBee-compliant wireless sensor network. In the proposed research, we will focus ona preliminary design of the monitoring terminal that integrates the functionalities of microphone, data sampling, and signal processing along with data communication through a ZigBee wireless channel. Sufficient compliance of the developed sound level meter and noise dosimeter with the related ANSI standards will be tested and demonstrated. Thisplan takes advantage of our broad knowledge in acoustic signal processing and ZigBee wireless sensor network, and will benefit from our experienceand skills with the development of embedded digital signal processing systems using either FPGA (field programmable gate array) or DSP (digital signal processor). The Phase I effort will provide a foundation for prototype design to be conducted in Phase II.


Grant
Agency: National Aeronautics and Space Administration | Branch: | Program: SBIR | Phase: Phase II | Award Amount: 749.98K | Year: 2012

The International Space Station (ISS) needs to keep quiet tomaintain a healthy and habitable environment in which crewmemberscan perform long-term and uninterrupted scientific researchunder microgravity conditions. Acoustic survey is now performedonce every two months using hand-held devices at 60 locationson the ISS. It takes a significant amount of precious crew timeand the sporadic monitoring program is not adequate. NASA hasdefined a need for an automated, continuous acoustic monitoringsystem that is efficient in power consumption (long battery life),accurate, highly integrated, wireless connected, scalable,small and lightweight. WeVoice Inc.\ proposed to develop aZigBee-based wireless sensor network for acoustic monitoringto meet the challenges. During Phase I of this projects, threeessential capabilities were developed, tested, and validated:* The design of a data collection subsystem that integratesmeasurement microphones and the feasibility of using thestate-of-the-art MEMS microphones.* The development of accurate and computationally efficientsignal processing algorithms for acoustic frequency(octave, 1/3-octave, and narrowband) analysis and soundlevel measurement.* The construction of a ZigBee network for data communication.In addition, the WeVoice SBIR research team has started workingon flight-like devices. Clear directions for improvement wereestablished for the Phase II efforts that may follow. The Phase IIprogram focuses on system integration and optimization,software implementation, and graphical user interface development.An in-situ calibration plan will be suggested and a demonstrablesystem will be delivered to NASA for testing in a ground facilityat the completion of the Phase II contract. So the expected TRLthen is expected to reach 6.


Trademark
WEVOICE, Inc. | Date: 2013-12-02

Apparatus for wireless transmission of acoustic information; Computer hardware for wireless content delivery; Computer software and hardware for recording, transmission, distribution, reception, processing, retrieval and reproduction of audio and speech.

Loading WEVOICE, Inc. collaborators
Loading WEVOICE, Inc. collaborators