This study's aim was to determine the relationship between Dermatology Life Quality Index (DLQI) scores and a Global Question (GQ) concerning patients' views of the overall impairment of their skin-related quality of life (QoL), and to express this relationship by identifying bands of DLQI scores equivalent to each GQ descriptor. A DLQI questionnaire and the GQ were mailed to 3834 adult general dermatology outpatients. There were 1993 (52%) responses: male 841; female 1152. Mean DLQI score = 4.86 (range 0-30, standard deviation (SD) = 5.83). Mean GQ score = 1.22 (range 0-4, SD = 1.20). The mean, mode, and median of the GQ scores for each DLQI score were used to devise several sets of bands of DLQI scores, and kappa coefficients of agreement calculated. The set proposed for adoption is: DLQI scores 0-1 = no effect on patient's life (GQ = 0, n = 754); DLQI scores 2-5 = small effect on patient's life (GQ = 1, n = 611); DLQI scores 6-10 = moderate effect on patient's life (GQ = 2, n = 327); DLQI scores 11-20 = very large effect on patient's life (GQ = 3, n = 242); DLQI scores 21-30 = extremely large effect on patient's life (GQ = 4, n = 59); kappa coefficient 0.489. Banding of the DLQI will aid the clinical interpretation of an individual's DLQI score and allow DLQI scores to inform clinical decisions.

No abstract

This paper describes a system that generates speaker-annotated transcripts of meetings by using a microphone array and a 360-degree camera. The hallmark of the system is its ability to handle overlapped speech, which has been an unsolved problem in realistic settings for over a decade. We show that this problem can be addressed by using a continuous speech separation approach. In addition, we describe an online audio-visual speaker diarization method that leverages face tracking and identification, sound source localization, speaker identification, and, if available, prior speaker information for robustness to various real world challenges. All components are integrated in a meeting transcription framework called SRD, which stands for "separate, recognize, and diarize". Experimental results using recordings of natural meetings involving up to 11 attendees are reported. The continuous speech separation improves a word error rate (WER) by 16.1% compared with a highly tuned beamformer. When a complete list of meeting attendees is available, the discrepancy between WER and speaker-attributed WER is only 1.0%, indicating accurate wordto-speaker association. This increases marginally to 1.6% when 50% of the attendees are unknown to the system.

Abstract-Speaker diarization is defined as the task of determining "who spoke when" given an audio track and no other prior knowledge of any kind. The following article shows how a state-of-the-art speaker diarization system can be improved by combining traditional short-term features (MFCCs) with prosodic and other long-term features. First, we present a framework to study the speaker discriminability of 70 different long-term features. Then, we show how the top-ranked long-term features can be combined with short-term features to increase the accuracy of speaker diarization. The results were measured on standardized datasets (NIST RT) and show a consistent improvement of about 30% relative in diarization error rate compared to the best system presented at the NIST evaluation in 2007.