Ohtani - REVERB Workshop 2014 ADAPTIVE DEREVERBERATION...

Info icon This preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
ADAPTIVE DEREVERBERATION METHOD BASED ON COMPLEMENTARY WIENER FILTER AND MODULATION TRANSFER FUNCTION Kento Ohtani , Tatsuya Komatsu , Takanori Nishino , and Kazuya Takeda Graduate School of Information Science, Nagoya University, Nagoya, Japan Graduate School of Engineering, Mie University, Tsu, Japan ABSTRACT Many methods for dereverberation of speech have been pro- posed, however most of these methods require large compu- tational resources. In this paper, we evaluate a method based on a complementary Wiener filter which requires very little computation. Because the filter coefficients used with this method have a large impact on dereverberation performance, we propose method to estimate these filter coefficients. Our filter estimation method is based on the observation that modulation transfer functions have inverse characteristics of dereverberation filter. We also use spectral subtraction for noise reduction and an ML estimator to estimate reverberation time. The results of our experimental evaluation show that our proposed method can effectively suppress reverberation with only a slight time delay. Index Terms dereverberation, real-time processing, single-channel, Wiener filter, modulation transfer function 1. INTRODUCTION Speech recognition technology is currently in use in appli- cations such as the voice call function of smart phones, for voice-activated information searches, and in other types of hands-free computer interfaces, and its use is rapidly spread- ing. These systems are often used in rooms, however, and when we use a microphone indoors, the reflection of sound waves from the walls, called reverberation, reduces the clar- ity of speech. Therefore, removing acoustic distortion from reverberant speech is an important issue, and many derever- beration techniques have been proposed. When we use dere- verberation methods with voice call and teleconferencing sys- tems, it is desirable that there be no delay due to computa- tional processing. Moreover, current dereverberation methods require additional filtering processes, such as noise reduction. However, most of the devices using these systems have lim- ited computational speed and resources. Thus, it is desirable to minimize computation during dereverberation. Lebart et al. proposed a single channel dereverberation technique using spectral subtraction (SS) [1]. They assumed that the late reverberant component of recorded speech is equal to the target speech, when time delay and amplitude attenuation are taken into consideration [2]. Unoki et al. pro- posed a dereverberation method based on restoration of the speech power envelope [3]. Using the conventional method, the speech power envelope component is first separated from reverberant speech. Then, the power envelope component is filtered and integrated with the carrier component.
Image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern