An objective evaluation of hearing aids and DNN-based speech enhancement in complex acoustic scenes

Gusó; Enric; Luberadzka, Joanna; Baig, Martí; Sayin, Umut; Serra, Xavier

An objective evaluation of hearing aids and DNN-based speech enhancement in complex acoustic scenes

Citació

Gusó E, Luberadzka J, Baig M, Sayin Saraç U, Serra X. An objective evaluation of hearing aids and DNN-based speech enhancement in complex acoustic scenes. In: Kim M, Bryan N, Bello J, Elhilali M, Cartwright M, Bittner R, Pruthi T, Giacobello D, Fuentes M, Nam J, Brandstein M, Yoshii K, Virtanen T, editors. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2023); 2023 Oct 22-25; New York: IEEE; 2023. 5 p. DOI: 10.1109/WASPAA58266.2023.10248112

Resum

We investigate the objective performance of five high-end commercially available Hearing Aid (HA) devices compared to DNN-based speech enhancement algorithms in complex acoustic environments. To this end, we measure the HRTFs of a single HA device to synthesize a binaural dataset for training two state-of-the-art causal and non-causal DNN enhancement models. We then generate an evaluation set of realistic speech-in-noise situations using an Ambisonics loudspeaker setup and record with a KU100 dummy head wearing each of the HA devices, both with and without the conventional HA algorithms, applying the DNN enhancers to the latter. We find that the DNN-based enhancement outperforms the HA algorithms in terms of noise suppression and objective intelligibility metrics.