Speaker Clustering in Speech Recognition
Olga Grebenskaya, Tomi Kinnunen, Pasi Fränti · 2005
The paper presents a combination of speaker and speech recognition techniques aiming to improve speech recognition rates. This combination is done by clustering the speaker models created from the training material. Speaker model is a codebook obtained by Vector Quantization (VQ) approach. We propose metaclustering algorithm to group codebooks into clusters and calculate the centroid codebooks. The last are thought as cluster representatives and used to determine the closest cluster on the recognition stage. We present the results of clustering under two conditions. First one keeps codebook size fixed and varies the number of clusters while the second one examines the impact of different cluster number on recognition results while codebook size is fixed.