Publication

Evaluating the Robustness of Privacy-Sensitive Audio Features for Speech Detection in Personal Audio Log Scenarios

Hervé Bourlard, Mathew Magimai Doss
2010
Reports

Abstract

Personal audio logs are often recorded in multiple environments. This poses challenges for robust front-end processing, including speech/nonspeech detection (SND). Motivated by this, we investigate the robustness of four different privacy-sensitive features for SND, namely energy, zero crossing rate, spectral flatness, and kurtosis. We study early and late fusion of these features in conjunction with modeling temporal context. These combinations are evaluated in mismatched conditions on a dataset of nearly 450 hours. While both combinations yielded improvements over individual features, generally feature combinations performed better. Comparisons with a state-of-the-art spectral based and a privacy-sensitive feature set are also provided.

Official source

https://infoscience.epfl.ch/entities/publication/19027647-a596-4018-ab67-c9ac5d51b500

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Hervé Bourlard, Mathew Magimai Doss
2010
Reports

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/19027647-a596-4018-ab67-c9ac5d51b500

About this result

Related concepts (11)

Privacy concerns with social networking services

Since the arrival of early social networking sites in the early 2000s, online social networking platforms have expanded exponentially, with the biggest names in social media in the mid-2010s being Facebook, Instagram, Twitter and Snapchat. The massive influx of personal information that has become available online and stored in the cloud has put user privacy at the forefront of discussion regarding the database's ability to safely store such personal information.

Aneutronic fusion

Aneutronic fusion is any form of fusion power in which very little of the energy released is carried by neutrons. While the lowest-threshold nuclear fusion reactions release up to 80% of their energy in the form of neutrons, aneutronic reactions release energy in the form of charged particles, typically protons or alpha particles. Successful aneutronic fusion would greatly reduce problems associated with neutron radiation such as damaging ionizing radiation, neutron activation, reactor maintenance, and requirements for biological shielding, remote handling and safety.

Fusion power

Fusion power is a proposed form of power generation that would generate electricity by using heat from nuclear fusion reactions. In a fusion process, two lighter atomic nuclei combine to form a heavier nucleus, while releasing energy. Devices designed to harness this energy are known as fusion reactors. Research into fusion reactors began in the 1940s, but as of 2023, no device has reached net power. Fusion processes require fuel and a confined environment with sufficient temperature, pressure, and confinement time to create a plasma in which fusion can occur.

Related publications (2)

Evaluating the Robustness of Privacy-Sensitive Audio Features for Speech Detection in Personal Audio Log Scenarios

Chat with Graph Search

The Speed Submission to DIHARD II: Contributions & Lessons Learned

The role of the sheath in magnetized plasma fluid turbulence