ASPIRE - Real noisy audio-visual speech enhancement corpus

Gogate, Mandar; Dashtipour, Kia; Adeel, Ahsan; Hussain, Amir

Abstract

ASPIRE is a a first of its kind, audiovisual speech corpus recorded in real noisy environment (such as cafe, restaurants) which can be used to support reliable evaluation of multi-modal Speech Filtering technologies. This dataset follows the same sentence format as the audio-visual Grid corpus. The recorded audiovisual speech corpus can be used for reliable evaluation of next generation multi-modal Speech Filtering technologies.

Citation

Gogate, M., Dashtipour, K., Adeel, A., & Hussain, A. (2020). ASPIRE - Real noisy audio-visual speech enhancement corpus. [Dataset]. https://doi.org/10.5281/zenodo.4585619

• Online Publication Date: Nov 1, 2020
• Publication Date: Nov 1, 2020
• Deposit Date: Apr 26, 2022
• DOI: https://doi.org/10.5281/zenodo.4585619
• Keywords: speech enhancement, speech separation, audio-visual, deep learning
• Public URL: http://researchrepository.napier.ac.uk/Output/2866106
• Collection Date: Jun 1, 2018