2020/04/30 by Deepak Baby, Arthur Van Den Broucke, Sarah Verhulst · 62 citations
Computer Science · Engineering · Neuroscience · #Acoustic Wave Phenomena Research #Artificial intelligence #Computer science #Convolutional neural network #Hearing Loss and Rehabilitation #Noise reduction #Nonlinear system #Speech and Audio Processing #Speech enhancement #Speech recognition #cs.CE #cs.LG #cs.SD #eess.AS
paper · pdf · doi:10.1038/s42256-020-00286-8
published in Nature Machine Intelligence 3(2), 134-143 (Nature Portfolio)
arxiv created 2020/12/04 · openalex publication_date 2021/02/08 · arxiv updated 2021/02/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Auditory models are commonly used as feature extractors for automatic speech-recognition systems or as front-ends for robotics, machine-hearing and hearing-aid applications. Although auditory models can capture the biophysical and nonlinear properties of human hearing in great detail, these biophysical models are computationally expensive and cannot be used in real-time applications. We present a hybrid approach where convolutional neural networks are combined with computational neuroscience to yield a real-time end-to-end model for human cochlear mechanics, including level-dependent filter tuning (CoNNear). The CoNNear model was trained on acoustic speech material and its performance and applicability were evaluated using (unseen) sound stimuli commonly employed in cochlear mechanics research. The CoNNear model accurately simulates human cochlear frequency selectivity and its dependence on sound intensity, an essential quality for robust speech intelligibility at negative speech-to-background-noise ratios. The CoNNear architecture is based on parallel and differentiable computations and has the power to achieve real-time human performance. These unique CoNNear features will enable the next generation of human-like machine-hearing applications.