meetingdiarisation

NEVER-ENDING LEARNING SYSTEM FOR ON-LINE SPEAKER DIARIZATION

Konstantin Markov and Satoshi Nakamura

National Institute of Information and Communications Technology
ATR Spoken Language Communication Research Labs., Japan

ABSTRACT
In this paper, we describe newhigh-performanceon-line speaker
diarization system which works faster than real-time and
has very low latency. It consists of several modules including
voice activity detection, novel speaker detection, speaker gender
and speaker identity classi􀂿cation. Allmodules share a set
of Gaussian mixturemodels (GMM) representing pause,male
and female speakers, and each individual speaker. Initially,
there are only three GMMs for pause and two speaker genders,
trained in advance from some data. During the speaker
diarization process, for each speech segment it is decidedwhether
it comes from a new speaker or from already known
speaker. In case of a new speaker, his/her gender is identi􀂿ed,
and then, from the corresponding gender GMM, a new GMM
is spawned by copying its parameters. This GMM is learned
on-line using the speech segment data and from this point it
is used to represent the new speaker. All individual speaker
models are produced in this way. In the case of an old speaker,
s/he is identi􀂿ed and the correspondingGMMis again learned
on-line. In order to prevent an unlimited grow of the speaker
model number, those models that have not been selected as
winners for a long period of time are deleted from the system.
This allows the system to be able to perform its task
inde􀂿nitely in addition to being capable of self-organization,
i.e. unsupervised adaptive learning, and preservation of the
learned knowledge, i.e. speakers. Such functionalities are attributed
to the so called Never-Ending Learning systems. For
evaluation, we used part of the TC-STAR database consisting
of European Parliament Plenary speeches. The results show
that this system achieves a speaker diarization error rate of
4.6% with latency of at most 3 seconds.
Index Terms— Speaker diarization, Speaker segmentation,
On-line GMM learning, Never-ending learning.