TY - JOUR AU - Yang, Jinchao AU - Zhang, Xiang AU - Suo, Hongbin AU - Lu, Li AU - Zhang, Jianping AU - Yan, Yonghong PY - 2012 DA - 2012/02/27 TI - Low-dimensional representation of Gaussian mixture model supervector for language recognition JO - EURASIP Journal on Advances in Signal Processing SP - 47 VL - 2012 IS - 1 AB - In this article, we propose a new feature which could be used for the framework of SVM-based language recognition, by introducing the idea of total variability used in speaker recognition to language recognition. We consider the new feature as low-dimensional representation of Gaussian mixture model supervector. Thus we propose multiple total variability (MTV) language recognition system based on total variability (TV) language recognition system. Our experiments show that the total factor vector includes the language dependent information; what's more, multiple total factor vector contains more language dependent information. SN - 1687-6180 UR - https://doi.org/10.1186/1687-6180-2012-47 DO - 10.1186/1687-6180-2012-47 ID - Yang2012 ER -