Publication Details

Enhancement and Analysis of Conversational Speech: JSALT 2017

RYANT Neville, BERGELSON Elika, CHURCH Kenneth, CRISTIA Alejandrina, DU Jun, GANAPATHY Sriram, KHUDANPUR Sanjeev, KOWALSKI Diana, KRISHNAMOORTHY Mahesh, KULSHRESHTA Rajat, LIBERMAN Mark, LU Yu-Ding, MACIEJEWSKI Matthew, METZE Florian, PROFANT Ján, SUN Lei, TSAO Yu and YU Zhou. Enhancement and Analysis of Conversational Speech: JSALT 2017. In: Proceedings of ICASSP 2018. Calgary: IEEE Signal Processing Society, 2018, pp. 5154-5158. ISBN 978-1-5386-4658-8.
Czech title
Zvýrazňování a analýza konverzační řeči: JSALT 2017
conference paper
Ryant Neville (UPENN)
Bergelson Elika (DUKE)
Church Kenneth (IBM)
Cristia Alejandrina (ENS)
Du Jun (USTC)
Ganapathy Sriram (IISC)
Khudanpur Sanjeev (JHU)
Kowalski Diana (UILLINOIS)
Krishnamoorthy Mahesh (Apple)
Kulshreshta Rajat (CMU)
Liberman Mark (UPENN)
Lu Yu-Ding (ASIN)
Maciejewski Matthew (JHU)
Metze Florian (CMU)
Profant Ján, Ing. (FIT BUT)
Sun Lei (USTC)
Tsao Yu (ASIN)
Yu Zhou (UCDavis)
diarization, overlap detection, speech enhancement, automatic speech recognition
Automatic speech recognition is more and more widely and effectively used. Nevertheless, in some automatic speech analysis tasks the state of the art is surprisingly poor. One of these is "diarization", the task of determining who spoke when. Diarization is key to processing meeting audio and clinical interviews, extended recordings such as police body cam or child language acquisition data, and any other speech data involving multiple speakers whose voices are not cleanly separated into individual channels. Overlapping speech, environmental noise and suboptimal recording techniques make the problem harder. During the JSALT Summer Workshop at CMU in 2017, an international team of researchers worked on several aspects of this problem, including calibration of the state of the art, detection of overlaps, enhancement of noisy recordings, and classification of shorter speech segments. This paper sketches the workshops results, and announces plans for a "Diarization Challenge" to encourage further progress.
Proceedings of ICASSP 2018
IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, CA
IEEE Signal Processing Society
Calgary, CA
   author = "Neville Ryant and Elika Bergelson and Kenneth Church and Alejandrina Cristia and Jun Du and Sriram Ganapathy and Sanjeev Khudanpur and Diana Kowalski and Mahesh Krishnamoorthy and Rajat Kulshreshta and Mark Liberman and Yu-Ding Lu and Matthew Maciejewski and Florian Metze and J\'{a}n Profant and Lei Sun and Yu Tsao and Zhou Yu",
   title = "Enhancement and Analysis of Conversational  Speech: JSALT 2017",
   pages = "5154--5158",
   booktitle = "Proceedings of ICASSP 2018",
   year = 2018,
   location = "Calgary, CA",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-5386-4658-8",
   doi = "10.1109/ICASSP.2018.8462468",
   language = "english",
   url = ""
Back to top