Language Recognition using Time Delay Deep Neural Network
This work addresses language recognition for speech processing applications, but it is incremental as it builds on existing I-vector and DNN methods.
The paper tackled language recognition by using a Time Delay Deep Neural Network as a universal background model in an I-vector framework, achieving results tested on fourteen languages with the ability to easily add new languages by retraining only a logistic regression model.
This work explores the use of a monolingual Deep Neural Network (DNN) model as an universal background model (UBM) to address the problem of Language Recognition (LR) in I-vector framework. A Time Delay Deep Neural Network (TDDNN) architecture is used in this work, which is trained as an acoustic model in an English Automatic Speech Recognition (ASR) task. A logistic regression model is trained to classify the I-vectors. The proposed system is tested with fourteen languages with various confusion pairs and it can be easily extended to include a new language by just retraining the last simple logistic regression model. The architectural flexibility is the major advantage of the proposed system compared to the single DNN classifier based approach.