An Active Machine Hearing System for Auditory Stream Segregation
This work addresses auditory stream segregation for machine hearing systems, but it is incremental as it builds on existing probabilistic methods with added head movements.
The study tackled the problem of auditory stream segregation in multi-source environments by developing a binaural machine hearing system that mimics human ability through probabilistic clustering and rotational head movements, achieving improved localization and segregation performance in scenarios with multiple speech and non-speech sounds.
This study describes a binaural machine hearing system that is capable of performing auditory stream segregation in scenarios where multiple sound sources are present. The process of stream segregation refers to the capability of human listeners to group acoustic signals into sets of distinct auditory streams, corresponding to individual sound sources. The proposed computational framework mimics this ability via a probabilistic clustering scheme for joint localization and segregation. This scheme is based on mixtures of von Mises distributions to model the angular positions of the sound sources surrounding the listener. The distribution parameters are estimated using block-wise processing of auditory cues extracted from binaural signals. Additionally, the proposed system can conduct rotational head movements to improve localization and stream segregation performance. Evaluation of the system is conducted in scenarios containing multiple simultaneously active speech and non-speech sounds placed at different positions relative to the listener.