You are here

Acoustic scene analysis

Acoustic scene analysis aims to process and interpret from different perspectives the acoustic information diffused in the environment and picked up by a multi-microphone acquisition system. Multi-source localization and tracking, detection and classification of acoustic events, source separation, speech enhancement, speaker identification represent some of the basic problems that are being investigated in order to characterize the acoustic scene. Based on a suitable use of the resulting information in the front-end processing stage, a distant-speech recognition task turns out to be less complex and prone to a reduced error rate. Acoustic scene analysis can also represent a pre-processing step in other application contexts as, for instance, smart videoconferencing and multi-modal human-computer interaction  (e.g. based on audio and video fusion).