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 7 of 7 for “"Voice Activity Detection"”.

  1. Neural Voice Activity Detection and its practical use

    The task of producing a Voice Activity Detector (VAD) that is robust in the presence of non-stationary background noise has been an active area of research for several decades. Historically, many of the proposed VAD models have been highly heuristic in nature. More recently, however, statistical …

    mit Repository record for Neural Voice Activity Detection and its practical use (opens in a new tab)

  2. Speech enhancement using multisensory cooperative computing

    … modes, by suppressing redundant synaptic activity. MCC establishes a paradigm for energy-efficient, high-capacity neuromorphic computing suited to real-time audio-visual learning. Second, to address AVSE on resource-constrained edge devices and the challenges of real-world noise, a novel …

    wlv Repository record for Speech enhancement using multisensory cooperative computing (opens in a new tab)

  3. Parkinsonian Speech and Voice Quality: Assessment and Improvement

    … nearly 90% of people impaired with PD develop voice and speech disorders. Speech production impairments in PD subjects typically result in hypophonia and consequently, poor speech signal-to-noise ratio (SNR) in noisy environments and inferior speech intelligibility and quality. Assessment, …

    uwo Repository record for Parkinsonian Speech and Voice Quality: Assessment and Improvement (opens in a new tab)

  4. Energy-scalable speech recognition circuits

    … (Kaldi) on the hardware platform. We investigate voice activity detection (VAD) as a wake-up mechanism and conclude that an accurate and robust algorithm is necessary to minimize system power, even if it results in larger area and power for the VAD itself. We design fixed-point digital …

    mit Repository record for Energy-scalable speech recognition circuits (opens in a new tab)

  5. On-device mobile speech recognition

    … the wireless client-server bottleneck. For the Voice Activity Detection part of this work, this thesis presents two novel algorithms used to detect speech activity within an audio signal. The first algorithm is based on the Log Linear Predictive Cepstral Coefficients Residual signal. These …

    nott-trent Repository record for On-device mobile speech recognition (opens in a new tab)

  6. Development of machine learning based speaker recognition system

    … system that is capable of recognizing its users’ voice using advanced machine learning and digital signal processing tools. The proposed system can both validate a person’s identity (i.e. verification) and recognize it from a larger known group of people (i.e. identification). We designed the …

    uiuc Repository record for Development of machine learning based speaker recognition system (opens in a new tab)

  7. Neural Time Alignment for End-to-End Automatic Speech Recognition Systems

    … encoder and decoder as the input, and deal with Voice Activity Detection (VAD). Unlike the LSyncNA module, the FSyncNA module uses dynamic programming (the Viterbi algorithm) to find out the absolute word-level time alignment, hence the inference phase of FSyncNA is slower than LSyncNA. …

    cambridge Repository record for Neural Time Alignment for End-to-End Automatic Speech Recognition Systems (opens in a new tab)