Complex Linear Projection (CLP): A Discriminative Approach to Joint Feature Extraction and Acoustic Modeling

Google Scholar


State-of-the-art automatic speech recognition (ASR) systems typically rely on pre-processed features. This paper studies the time-frequency duality in ASR feature extraction methods and proposes extending the standard acoustic model with a complex-valued linear projection layer to learn and optimize features that minimize standard cost functions such as cross entropy. The proposed Complex Linear Projection (CLP) features achieve superior performance compared to pre-processed Log Mel features.