Multichannel acoustic source and image dataset for the cocktail party effect in hearing aid and implant users

Abstract

The Cocktail Party Effect refers to the ability of the human sense of hearing to extract a specific target sound source from a mixture of background noises in complex acoustic scenarios. The ease with which normal hearing people perform this challenging task is in stark contrast to the difficulties that hearing-impaired subjects face in these situations. To help patients with hearing aids and implants, scientists are trying to imitate this ability of human hearing, with modest success so far. To support the scientific community in its efforts, we provide the Bern Cocktail Party (BCP) dataset consisting of 55938 Cocktail Party scenarios recorded from 20 people and a head and torso simulator wearing cochlear implant audio processors. The data were collected in an acoustic chamber with 16 synchronized microphones placed at purposeful positions on the participants’ heads. In addition to the multi-channel audio source and image recordings, the spatial coordinates of the microphone positions were digitized for each participant. Python scripts were provided to facilitate data processing.

Measurement(s)	acoustic Cocktail Party scenarios • acoustic composition of speech • Noise
Technology Type(s)	head-mounted microphones
Factor Type(s)	head shape of the participants • acoustic Cocktail Party scenarios played
Sample Characteristic - Organism	Homo sapiens

Machine-accessible metadata file describing the reported data: https://doi.org/10.6084/m9.figshare.13181921