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 10 of 10 for “"VoxCeleb"”.

  1. Automatic speaker verification and diarization on VoxCeleb data collection

    … good models. Current datasets include NIST SRE, VoxCeleb, etc. In this work, to collect a non-English speaking dataset, the pipeline of VoxCeleb data collection is adopted to collect an East Asian language-speaking Celebrities (EACeleb) dataset. To remove some noisy segments of the output and …

    gatech Repository record for Automatic speaker verification and diarization on VoxCeleb data collection (opens in a new tab)

  2. Odhad obličeje z řečového signálu

    … GAN. V této práci byly použity datasety VGGFace, VoxCeleb. Pro účely bakalářské práce byl vytvořen malý audiovizuální dataset česky mluvících osob. Práce je implementovaná pomocí skriptovacího jazyka Python s využitím knihovny PyTorch.

    brno-tech Repository record for Odhad obličeje z řečového signálu (opens in a new tab)

  3. Interpretace neuronových sítí ve zpracování řeči

    … datasetu a klasifikácia rečníka z filter bánk VoxCeleb datasetu s použitím konvolučnej a reziduálnej neurónovej siete. Na interpretáciu týchto neurónových sietí bola použitá metóda propagácie relevancií cez vrstvy. Táto metóda vytvorí tepelnú mapu, ktorá vyznačí príznaky, ktoré prispeli ku …

    brno-tech Repository record for Interpretace neuronových sítí ve zpracování řeči (opens in a new tab)

  4. Does Accept or Reject Give the Full Story: How Can Uncertainty be Quantified to Fill in the Blanks for Automatic Speaker Verification ?

    … analysis (PLDA) system. Experiments with Voxceleb and MUSAN datasets showed that the estimated uncertainty is associated with noise level, while utterance length is associated with uncertainty in the model or the level of knowledge. As the Bayesian framework is computationally intensive …

    unsw Repository record for Does Accept or Reject Give the Full Story: How Can Uncertainty be Quantified to Fill in the Blanks for Automatic Speaker Verification ? (opens in a new tab)

  5. Non-Parallel Voice Conversion

    … kvality, zejména z veřejně dostupné databáze VoxCeleb. Práce vychází z moderní architektury AutoVC definované Qianem et al. Je založena na neurálních autoenkodérech, jejichž cílem je oddělit informace o obsahu a řečníkovi do samostatných nízkodimenzionýálních vektorových reprezentací …

    brno-tech Repository record for Non-Parallel Voice Conversion (opens in a new tab)

  6. Automated Speaker Recognition in Non-ideal Audio Signals Using Deep Neural Networks

    … SITW, NIST SRE (2008, 2010, and 2018), Fisher, VOXCeleb, and JukeBox datasets convey the efficacy of the proposed techniques and their importance in improving speaker recognition performance in non-ideal audio conditions.

    msu Repository record for Automated Speaker Recognition in Non-ideal Audio Signals Using Deep Neural Networks (opens in a new tab)

  7. Modelos Neurais Auto-organizados em Interação Humano-Robô por Fala

    … lizam as bases Google commands, LibriSpeech, VoxCeleb, Aurora 4 e Chime 2 e no módulo SAoIHR-NLU utilizam as bases GPSR e HURIC. Os experimentos alcançaram resultados satisfatórios quando aplicados ao contexto robótico com palavras isoladas e sentenças em ambiente com ruído, para ampliação de …

    brazil-ufpe Repository record for Modelos Neurais Auto-organizados em Interação Humano-Robô por Fala (opens in a new tab)

  8. Video understanding using multimodal deep learning

    … audio-visual dataset of human speech called VoxCeleb, training on which yields state of the art models for speaker recognition; Second we train a text-based model to predict action labels from transcribed speech alone, and transfer these labels to accompanying videos. Training with these …

    oxford Repository record for Video understanding using multimodal deep learning (opens in a new tab)

  9. Edge Device Speaker Verification

    … of the publically available LibriSpeech and VoxCeleb datasets to train several small, generalizable, speaker verification models. Models trained on this data include those implementing recurrent and convolutional neural network architectures. In order to deploy our inference system to a …

    cuny Repository record for Edge Device Speaker Verification (opens in a new tab)