Voiced/unvoiced pattern-based duration modeling for language identification

摘要

Most existing duration modeling approaches facilitates phone recognizer and require manually annotated corpus to train the segmentation models, which is usually cost- and time-consuming. In this paper, a novel duration modeling approach is proposed, which does not require phone recognizer/annotated training data, and facilitates fast computation of language identification. In this approach, the segmentation is implemented by using articulatory features like voicing status. A pair of connected unvoiced and voiced segments is considered as the unit, and the duration of each segment is normalized for each utterance and then quantized into 20 discrete ranges. The ranges of units are later considered as symbol sequences and are modeled by n-gram models, to capture the temporal pattern, which is hypothesized to vary in different languages. The experiments based on the NIST LRE 2005 tasks show a relative 19.7% EER improvement by introducing the proposed duration modeling-based system into a fusion system containing two GMM-UBM based acoustic systems using MFCC and pitch+intensity features.