HIDVAS: A Hearing Instrument Dataset in Various Acoustical Scenarios for Algorithm Evaluation and Training [Full version including license-restricted material]

This repository contains all recordings related to the HIDVAS dataset. Due to license restrictions related to the recordings of the Leuven intelligibility sentences test spoken by a female speaker (LISTf) and Leuven intelligibility sentences test spoken by a male speaker (LISTm) material, this repository is not openly available. An openly accessible version of this dataset is available at [1]. To evaluate the performance of audio signal processing algorithms and to train data-driven algorithms, e.g., as applied in hearing instruments, either simulated or recorded data can be used. While large batches of simulated data can be generated using mathematical models, recorded data provide a more adequate representation of real-life scenarios. Therefore, in this paper, the Hearing Instrument Dataset in Various Acoustical Scenarios (HIDVAS) is introduced. This dataset consists of both impulse responses and audio recordings using eight external loudspeakers, two external microphones, and a dummy head. On this dummy head behind-the-ear (BTE) hearing instrument shells with two microphones per shell are mounted, and in the dummy head’s ears receiver-in-canal (RIC) hearing instrument loudspeakers are inserted. The dummy head also contains microphones located at its eardrum. The impulse responses have been computed from a swept-sine recording for each microphone-loudspeaker pair, and the audio recordings have been obtained by playing back audio (male and female speech, speech shaped noise, singing voice, stringed instrument, wind instrument, and percussion instrument) through each individual loudspeaker and recording simultaneously using all microphones. These recordings have been repeated for four hearing instrument domes (open, semi-open, closed, and no-RIC) in three reverberation conditions in one room (T30 = 0.09 s, T30 = 0.47 s, and T30 = 0.73 s), and in one reverberation condition in a different room (T30 = 1.48 s). The usage of the dataset as a ‘hearing instrument in a box’ is exemplified with three example use cases. To this end, the ipsilateral feedback paths, the ratio of direct-to-reverberant sound energy in an external microphone close to the sound source versus in the BTE hearing instrument microphones, and the leakage from external sound sources to the eardrum are studied. The feedback and leakage for the open and semi-open domes are similar and substantially larger than for the closed dome. The ratio of the direct-to-reverberant sound energy in the BTE hearing instrument microphones is lower than in the external microphone, and this difference increases with the reverberation time.A preprint is available at [2]. [1] Roebben, A., Bernardi, G., Wouters, J., van Waterschoot, T., Moonen, M.: HIDVAS: A Hearing Instrument Dataset in Various Acoustical Scenarios for Algorithm Evaluation and Training [Full version including license-restricted material]. Zenodo (2026). https://doi.org/10.5281/zenodo.15773862[2] Roebben, A., Bernardi, G., Wouters, J., van Waterschoot, T., Moonen, M.: HIDVAS: A Hearing Instrument Dataset in Various Acoustical Scenarios for Algorithm Evaluation and Training. arXiv (2026). https://doi.org/10.48550/arXiv.2606.14175