Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

An LLR-Based Technique for Frame Selection for GMM-Based Text-Independent Speaker Identification

Pang Kuen Tsoi, Pascale Fung

Human Language Technology Center Hong Kong University of Science and Technology

In speaker recognition systems, frame selection, which aims at determining which frame is useful and which is not and selecting useful frames from the test utterance, can be utilized to increase recognition accuracy. In this paper, we present a new approach for frame selection using Log Likelihood Ratio (LLR), which is based on the idea that if a frame contains speaker information, the Log likelihood Score of the corresponding speaker model will be much larger than that of its competing model. As a result, for each frame we can calculate the Log Likelihood Ratio (LLR) between the largest score and the second largest score in different speaker models and take it as a reference: Those frames with a small LLR can be rejected and those with a large LLR can be kept. This algorithm is implemented based on a GMM-based text-independent speaker identification system. We compare the algorithm with another frame selection approach based on Jensen Difference (ID). Experiment shows that the approach using SD reduces the error by about 39,34%, while our approach using LLR reduces the error by about 46.32%.

Full Paper

Bibliographic reference.  Tsoi, Pang Kuen / Fung, Pascale (2000): "An LLR-based technique for frame selection for GMM-based text-independent speaker identification", In ICSLP-2000, vol.2, 274-277.