We introduce Audvert – a system that facilitates serendipitous discovery and navigation through spatial audio; used to navigate and discover points of interest in large, unfamiliar indoor environments. Our main aim was to create a lightweight spatial audio display that can convey a sense of a place without complex point and select interactions. We conducted a preliminary study comparing two aud...

Most of current Video Copy Detection systems (VCD) perform a multimodal detection by dividing the system into subsystems. Each subsystem performs a copy detection using a different feature (either visual or audio), and the sets of candidates are combined (fused) to create the final result. We present a VCD system that fuses visual and audio descriptors at the similarity search level. The system...

An intelligent audio system for sound design using artificial intelligence techniques is reported. The system is used to analyse acoustic recordings, extract salient sound features and to process them to generate parameters for sound synthesis, in a manner that mimics human audio experts. Preliminary tests show that the use of the system reduces design time and yet the quality of the resulting ...

An audio-visual localisation and tracking system for meeting scenarios is presented which draws its inspiration from neurobiological processing. Meetings are recorded by a KEMAR binaural manikin and a single camera placed directly above the manikin. Source localisation from the binaural audio and face, object and motion locations from the video frames are used as input to two linked neural osci...

SoundSpotter is an open source software system for real-time matching of an audio input stream to a database of continuous audio or video. Among its novel features are real-time control over audio segmentation, feature selection and match radius. The system uses audio input to control selection of output from a database using similarity-based matching. The low latency methods employed create a ...

We compare automatic recognition with human perception of audio-visual speech, in the large-vocabulary, continuous speech recognition (LVCSR) domain. Specifically, we study the benefit of the visual modality for both machines and humans, when combined with audio degraded by speech-babble noise at various signal-to-noise ratios (SNRs). We first consider an automatic speechreading system with a p...