Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

INCREMENTAL TRANSFER LEARNING IN TWO-PASS INFORMATION BOTTLENECK BASED SPEAKER DIARIZATION SYSTEM FOR MEETINGS

Abstract: 

The two-pass information bottleneck (TPIB) based speaker diarization system operates independently on different conversational recordings. TPIB system does not consider previously learned speaker discriminative information while diarizing new conversations. Hence, the real time factor (RTF) of TPIB system is high owing to the training time required for the artificial neural network (ANN). This paper attempts to improve the RTF of the TPIB system using an incremental transfer learning approach where the parameters learned by the ANN from other conversations are updated using current conversation rather than learning parameters from scratch. This reduces the RTF significantly. The effectiveness of the proposed approach compared to the baseline IB and the TPIB systems is demonstrated on standard NIST and AMI conversational meeting datasets. With a minor degradation in performance, the proposed system shows a significant improvement of 33.07% and 24.45% in RTF with respect to TPIB system on the NIST RT-04Eval and AMI-1 datasets, respectively.

up
0 users have voted:

Paper Details

Authors:
Srikanth Madikeri, C Chandra Sekhar, Hema A Murthy
Submitted On:
8 May 2019 - 9:21am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Nauman Dawalatabad
Paper Code:
5236
Document Year:
2019
Cite

Document Files

icassp2019_sd_poster.pdf

(28)

Subscribe

[1] Srikanth Madikeri, C Chandra Sekhar, Hema A Murthy, "INCREMENTAL TRANSFER LEARNING IN TWO-PASS INFORMATION BOTTLENECK BASED SPEAKER DIARIZATION SYSTEM FOR MEETINGS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4092. Accessed: Dec. 06, 2019.
@article{4092-19,
url = {http://sigport.org/4092},
author = {Srikanth Madikeri; C Chandra Sekhar; Hema A Murthy },
publisher = {IEEE SigPort},
title = {INCREMENTAL TRANSFER LEARNING IN TWO-PASS INFORMATION BOTTLENECK BASED SPEAKER DIARIZATION SYSTEM FOR MEETINGS},
year = {2019} }
TY - EJOUR
T1 - INCREMENTAL TRANSFER LEARNING IN TWO-PASS INFORMATION BOTTLENECK BASED SPEAKER DIARIZATION SYSTEM FOR MEETINGS
AU - Srikanth Madikeri; C Chandra Sekhar; Hema A Murthy
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4092
ER -
Srikanth Madikeri, C Chandra Sekhar, Hema A Murthy. (2019). INCREMENTAL TRANSFER LEARNING IN TWO-PASS INFORMATION BOTTLENECK BASED SPEAKER DIARIZATION SYSTEM FOR MEETINGS. IEEE SigPort. http://sigport.org/4092
Srikanth Madikeri, C Chandra Sekhar, Hema A Murthy, 2019. INCREMENTAL TRANSFER LEARNING IN TWO-PASS INFORMATION BOTTLENECK BASED SPEAKER DIARIZATION SYSTEM FOR MEETINGS. Available at: http://sigport.org/4092.
Srikanth Madikeri, C Chandra Sekhar, Hema A Murthy. (2019). "INCREMENTAL TRANSFER LEARNING IN TWO-PASS INFORMATION BOTTLENECK BASED SPEAKER DIARIZATION SYSTEM FOR MEETINGS." Web.
1. Srikanth Madikeri, C Chandra Sekhar, Hema A Murthy. INCREMENTAL TRANSFER LEARNING IN TWO-PASS INFORMATION BOTTLENECK BASED SPEAKER DIARIZATION SYSTEM FOR MEETINGS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4092