NDLTD logo NDLTD Union Catalog and Global ETD Search

Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 9 of 9 for “"dereverberation"”.

  1. Implementation of short-time homomorphic dereverberation.

    Caldwell, James LewisMassachusetts Institute of Technology1971

    Massachusetts Institute of Technology. Dept. of Electrical Engineering. Thesis. 1971. M.S.

    mit Repository record

  2. Statistical impulse reponse modeling and dereverberation for room acoustics

    Wu, Tsan-MingGeorgia Institute of Technology2000

    gatech Repository record

  3. A comparative evaluation of two acoustic signal dereverberation techniques

    Gallemore, James BruceMassachusetts Institute of Technology1976

    Thesis (Elec. E.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science; and, (M.S.)--Massachusetts Institute of Technology, Dept. of Ocean Engineering, 1976.

    mit Repository record

  4. Single-Microphone Speech Dereverberation: Modulation Domain Processing and Quality Assessment

    Zheng, Chenxi2011

    … the past few years. Although multiple channel dereverberation methods provide some improvements in speech quality/ intelligibility, single-channel dereverberation remains an open challenge. Two types of advanced single-channel dereverberation methods, namely acoustic domain spectral subtraction …

    queens Repository record

  5. Toward More Intelligible Simultaneous Multi-channel Speech Enhancement and Recognition

    Ni, ZhaohengThe Graduate School and University Center of The City University of New York2027

    … into the multi-channel speech enhancement and dereverberation network further reduces the word error rate (WER) metric for the downstream ASR task.</p>

    cuny-grad Repository record

  6. Multi-modal and deep learning for robust speech recognition

    Feng, Xue, Ph. D. Massachusetts Institute of TechnologyMassachusetts Institute of Technology2017

    … we explored a speech feature denoising and dereverberation method via deep denoising autoencoders (DDA). The method was evaluated on the CHiME2-WSJ0 corpus and achieved a 16% to 25% absolute improvement in word error rate (WER) compared to the baseline. Third, we developed a method to …

    mit Repository record

  7. On entropic and compositional sound and its sources

    da Rocha Bragança Rodrigues, Jocelino AlexandreUniversity of Cambridge2021

    … time and is contrasted with results obtained via dereverberation (i.e. removing the effect of pressure build up due to acoustic reflections). Indirect noise transfer functions are calculated using the acoustic and compositional measurements, and issues pertaining to the methods applied are …

    cambridge Repository record

  8. Statistical Model Based Multi-Microphone Speech Processing: Toward Overcoming Mismatch Problem

    Kim, Lae-HoonUniversity of Illinois at Urbana-Champaign2010

    … purposes, we can have good demixing or dereverberation results. Finally, IBM estimation and ASR are jointly formulated under a GEM framework. Even with the optimal front-end pre-processing, there always exists a mismatched portion with the statistical speech process model which is going …

    uiuc Repository record

  9. Example-based audio editing

    Anushiravani, RaminUniversity of Illinois at Urbana-Champaign2017

    Traditionally, audio recordings are edited through digital audio workstations (DAWs), which give users access to different tools and parameters through a graphical user interface (GUI) without prior knowledge in coding or signal processing. The complexity of working with DAWs and the undeniable …

    uiuc Repository record