TY - GEN
T1 - A Class-dependent Background Model for Speech Signal Feature Extraction
AU - Jiang, Yuechi
AU - Frank Leung, H. F.
PY - 2018/11/19
Y1 - 2018/11/19
N2 - Universal Background Model (UBM) has been successfully applied to many speech signal classification tasks, such as speaker recognition and microphone recognition. UBM is used to form Gaussian Supervector (GSV) or i-vector, which is a good feature vector representing a piece of speech signal. In this paper, we propose another background model called Class-dependent Background Model (CBM), which makes use of class labels. UBM is completely a generative model, while CBM can be both generative and discriminative. Under some conditions, CBM can consume less time to be constructed than UBM. We also compare the performance of UBM and CBM as the background model to form GSV and i-vector for doing speaker recognition, microphone recognition, and telephone session recognition. Experimental results show that CBM performs very well and can be even better than UBM in most cases.
AB - Universal Background Model (UBM) has been successfully applied to many speech signal classification tasks, such as speaker recognition and microphone recognition. UBM is used to form Gaussian Supervector (GSV) or i-vector, which is a good feature vector representing a piece of speech signal. In this paper, we propose another background model called Class-dependent Background Model (CBM), which makes use of class labels. UBM is completely a generative model, while CBM can be both generative and discriminative. Under some conditions, CBM can consume less time to be constructed than UBM. We also compare the performance of UBM and CBM as the background model to form GSV and i-vector for doing speaker recognition, microphone recognition, and telephone session recognition. Experimental results show that CBM performs very well and can be even better than UBM in most cases.
KW - class-dependent background model
KW - Gaussian supervector
KW - i-vector
KW - speech signal classification
KW - universal background model
UR - http://www.scopus.com/inward/record.url?scp=85062791506&partnerID=8YFLogxK
U2 - 10.1109/ICDSP.2018.8631583
DO - 10.1109/ICDSP.2018.8631583
M3 - Conference article published in proceeding or book
AN - SCOPUS:85062791506
T3 - International Conference on Digital Signal Processing, DSP
BT - 2018 IEEE 23rd International Conference on Digital Signal Processing, DSP 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 23rd IEEE International Conference on Digital Signal Processing, DSP 2018
Y2 - 19 November 2018 through 21 November 2018
ER -