Close-talking differential microphone arrays (CTMAs) are useful in situations where the background noise level is very high because they inherently suppress farfield noise while emphasizing desired nearfield signals. One problem, however, is that the array has to be placed as close to the desired

Abstract. Laughter is a key element of human-human interaction, occurring surprisingly frequently in multi-party conversation. In meetings, laughter accounts for almost 10 % of vocalization effort by time, and is known to be relevant for topic segmentation and the automatic characterization of affect. We present a system for the detection of laughter, and its attribution to specific participants, which relies on simultaneously decoding the vocal activity of all participants given multi-channel recordings. The proposed framework allows us to disambiguate laughter and speech not only acoustically, but also by constraining the number of simultaneous speakers and the number of simultaneous laughers independently, since participants tend to take turns speaking but laugh together. We present experiments on 57 hours of meeting data, containing almost 11000 unique instances of laughter. 1

Vocal activity detection in close-talk microphone recordings of multiparty conversation continues to pose problems for meeting recognition systems, as evidenced by a 2-3 % absolute gap in word error rates achieved with automatic and manual segmentations. State-of-the-art segmentation systems

challenge. This paper provides a overview of DSR systems based on microphone arrays. In particular, we present recent work on acoustic beamforming for DSR, along with experimental results verifying the effectiveness of the various algorithms described here; beginning from a word error rate (WER) of 14

compared to close-talking microphones. Speaker direction information is derived from the filter coefficients of an adaptive Filter-and-Sum Beamformer and is combined with BIC analysis. The experimental results reveal significant improvements compared to BIC-only change detection, be it with the distant

In this paper the FAU IISAH corpus and its recording conditions are described: a new speech database consisting of human-machine and human-human interaction recordings. Beside close-talking microphones for the best possible audio quality of the recorded speech, far-distance microphones were used

in different acoustical environments, and when a desk-top microphone (rather than a close-talking microphone) is used for speech input. Without such processing, mismatches between training and testing conditions produce an unacceptable degradation in recognition accuracy. Two kinds of

-field (table-top) microphones. The close-talking microphones enable separation of each person’s audible activities from those of every other participant. The far-field microphones provide a view of the meeting as a whole. The transcripts preserve words and other communicative phenomena, displayed in musical

Abstract: Using the computational auditory scene analysis (CASA) as a framework, a novel speech separation approach based on dual-microphone energy difference (DMED) is proposed for close-talk system. The energy levels of the two microphones are calculated in time-frequency (T-F) units. The DMEDs

-free acquisition and directional discrimination, microphone arrays present a potential alternative to close-talking microphones in such an application. We first propose an appropriate microphone array geometry and improved processing technique for this scenario, paying particular attention to speaker separation