Browse Senior Theses - Electrical and Computer Engineering by Contributor "Hasegawa-Johnson, Mark"

  • Uppal, Karan (2012-05)
    This thesis explores the use of clustering algorithms in acoustic heart monitoring systems to detect the points of occurrence for a heartbeat. The proposed technique recovers heartbeats from an acoustically recorded ...

    application/pdf

    application/pdfPDF (4MB)Restricted to U of Illinois
  • Bharadwaj, Sujeeth (2009-12)
    A recent result in compressed sensing (CS) allows us to perform non-parametric speech recognition that is robust to noise, and that requires few training examples. By taking fixed length representations of training samples ...

    application/pdf

    application/pdfPDF (127kB)Restricted to U of Illinois
  • Hoffer-Sohn, Yda (2019-05)
    Most widely spoken languages have numerous dialects or accents which can vary in degree of mutual intelligibility between speakers and automatic speech recognition systems alike. Oftentimes it is difficult or costly to ...

    application/pdf

    application/pdfPDF (1MB)Restricted to U of Illinois
  • Jones, Jonathan (2014-05)
    Although current methods for automatically labeling a speech corpus have significantly reduced the amount of time and effort required by this once- tedious task, they still depend greatly on the existence of a labeled ...

    application/pdf

    application/pdfPDF (601kB)Restricted to U of Illinois
  • Yeh, Raymond (2014-05)
    This thesis addresses the problem of the high computation complexity issue that arises when decoding hidden Markov models (HMMs) with a large number of states. A novel approach, the two-beam Viterbi, with an extra forward ...

    application/pdf

    application/pdfPDF (1MB)
  • Xu, Yijia (2017-05)
    Automatic speech recognition (ASR) permits effective interaction between humans and machines in environments where typing is impossible. Some environments, however, are more difficult than others: acoustic noise disrupts ...

    application/pdf

    application/pdfPDF (1MB)Restricted to U of Illinois
  • Wang, Liming (2018-05)
    Automatic speech recognition (ASR) technologies have been successfully applied to most of the major languages in the world. However, ASR performs poorly with under-resourced languages such as Mboshi because those languages ...

    application/pdf

    application/pdfPDF (1MB)Restricted to U of Illinois
  • Harwath, David (2010-05)
    This paper presents a method of augmenting shifted-delta cepstral coefficients (SDCCs) with the classification outputs of an array of support vector machines (SVMs) trained to detect a set of manner and place features on ...

    application/pdf

    application/pdfPDF (793kB)Restricted to U of Illinois
  • Qian, Kaizhi (2014-05)
    Speaker adaptation based on the Universal Background Model (UBM) has become a standard approach for speaker recognition. A GMM supervector is constructed by normalizing and stacking the means of the adapted mixture components, ...

    application/pdf

    application/pdfPDF (342kB)
  • Yargop, Rahul U. (2008-12)
    This project is aimed at taking the first steps towards the creation of a "landscape map" by testing whether or not the sonorant feature is a relevant feature in language identification. Sonorant sounds are those with free ...

    application/pdf

    application/pdfPDF (967kB)Restricted to U of Illinois
  • Shin, Dongeek (2011-12)
    In this thesis, we present a technique for bandwidth extension (BWE) of a narrow-band (0 - 4 kHz) signal using articulatory features. The proposed technique recovers high-band components (4 - 8 kHz) through Gaussian ...

    application/pdf

    application/pdfPDF (1000kB)Restricted to U of Illinois
  • Wang, Lu (2018-05)
    This thesis presents a method to improve quality of synthesized speech by reducing the vocoded effect. The synthesis model takes mel-cepstral coefficients and spectrum envelopes as features of the original speech waveform. ...

    application/pdf

    application/pdfPDF (420kB)
  • Morshed, Mahir (2019-05)
    The use of end-to-end neural network architectures for speech recognition applications has brought a transition from using mappings of a speech signal's frequency spectra as inputs for a model to using the frequency ...

    application/pdf

    application/pdfPDF (568kB)Restricted to U of Illinois