bioeng_admin
2004-03-29 22:48:36
0
86
안녕하세요. 귀한 분을 모시고 다음과 같이 세미나를 갖습니다. 많은 참석 부탁드립니다.
학부생들과 이번에 새로 입학하신 대학원생들은 꼭 참석하셔서 현재 6층Computational neurosys lab에서 어떤 연구를 진행하는지 한번쯤 들어보실수있는 기회가 되기를 바랍니다.
때 : 2004년 3월 29일 월요일 늦은 2시 30분~4시
곳: 정문술 빌딩 217호
주제 : Learning and Analyzing Auditory Scenes with Probabilistic
Graphical Models
연사 : Te-Won Lee, Institute for Neural Computation, University of
California, San Diego
Abstract:
The problem of analyzing sound signals captured in auditory scenes has
attracted much attention from many different viewpoints. Auditory scenes
contain multiple sources that often emit sounds simultaneously. Sensors
located on the scene capture the sounds as they propagate away from the
sources. This talk focuses on algorithms for processing the sensor
signals to extract specific information about the auditory scene, the
sound sources it contains, and the signals they emit. Our approach is
based on the framework of probabilistic graphical models, developed in
the field of machine learning, and leverages on learning and reasoning
with those models. First, we present machine learning algorithms using
graphical models for speech signal representation. Learning efficient
codes for speech signals in a linear generative model allows us to
analyze important speech features and their characteristics to model
different sounds, individual speaker characteristics or classes of
speakers. Then, we use this principle to derive a method for solving the
difficult problem of separating multiple sources given only a single
channel microphone recording. Multi-channel observations can relax some
of the constraints in blind source separation. However, this problem now
includes reverberations, sensor noise and other real environment
challenges. We demonstrate solutions that can separate speech signals
from mixture recordings. Finally, we present ideas on how to extend from
the source separation methods to auditory scene analysis within the
graphical model framework. We discuss what computational challenges and
approximate solutions exist.
학부생들과 이번에 새로 입학하신 대학원생들은 꼭 참석하셔서 현재 6층Computational neurosys lab에서 어떤 연구를 진행하는지 한번쯤 들어보실수있는 기회가 되기를 바랍니다.
때 : 2004년 3월 29일 월요일 늦은 2시 30분~4시
곳: 정문술 빌딩 217호
주제 : Learning and Analyzing Auditory Scenes with Probabilistic
Graphical Models
연사 : Te-Won Lee, Institute for Neural Computation, University of
California, San Diego
Abstract:
The problem of analyzing sound signals captured in auditory scenes has
attracted much attention from many different viewpoints. Auditory scenes
contain multiple sources that often emit sounds simultaneously. Sensors
located on the scene capture the sounds as they propagate away from the
sources. This talk focuses on algorithms for processing the sensor
signals to extract specific information about the auditory scene, the
sound sources it contains, and the signals they emit. Our approach is
based on the framework of probabilistic graphical models, developed in
the field of machine learning, and leverages on learning and reasoning
with those models. First, we present machine learning algorithms using
graphical models for speech signal representation. Learning efficient
codes for speech signals in a linear generative model allows us to
analyze important speech features and their characteristics to model
different sounds, individual speaker characteristics or classes of
speakers. Then, we use this principle to derive a method for solving the
difficult problem of separating multiple sources given only a single
channel microphone recording. Multi-channel observations can relax some
of the constraints in blind source separation. However, this problem now
includes reverberations, sensor noise and other real environment
challenges. We demonstrate solutions that can separate speech signals
from mixture recordings. Finally, we present ideas on how to extend from
the source separation methods to auditory scene analysis within the
graphical model framework. We discuss what computational challenges and
approximate solutions exist.
