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 3 of 3 for “"Audio Perturbations"”.

  1. Multi-Dimensional Approaches to Hate Speech Detection

    … to structured, speaker-specific adversarial perturbations. We introduce a speaker-level compositional perturbation frame- work that learns structured, speaker-specific audio perturbations. This approach successfully compromises 92% of samples and 93% of speakers, remains computationally …

    unsw Repository record for Multi-Dimensional Approaches to Hate Speech Detection (opens in a new tab)

  2. End-to-end deep learning for audio classification: from waveforms to a security perspective

    Audio processing is one of the challenging problems in machine learning. Deep learning models have recently had a significant impact on sound processing problems such as audio classification, speech recognition, speaker identification, etc. Most of the methods based on deep models usually rely on …

    ets-quebec Download PDF for End-to-end deep learning for audio classification: from waveforms to a security perspective (opens in a new tab)

  3. SoundBreak: Studying vulnerabilities exposed by Audio Adversarial Attacks on Trimodal Models

    Foundation models that jointly process audio, visual, and textual inputs have demonstrated strong performance across a wide range of reasoning and generation tasks. Despite these advances, the robustness of such systems against adversarial manipulation remains insufficiently explored. This thesis …

    vt Repository record for SoundBreak: Studying vulnerabilities exposed by Audio Adversarial Attacks on Trimodal Models (opens in a new tab)