Fusion of Embeddings Networks for Robust Combination of Text Dependent and Independent Speaker Recognition
This work addresses the need for reliable speaker identification in applications like voice assistants, but it is incremental as it builds on existing ensemble and fusion techniques.
The paper tackles the problem of combining text-dependent and text-independent speaker recognition models into a robust ensemble system that handles incomplete inputs, achieving higher accuracy than baseline methods, particularly when inputs are missing.
By implicitly recognizing a user based on his/her speech input, speaker identification enables many downstream applications, such as personalized system behavior and expedited shopping checkouts. Based on whether the speech content is constrained or not, both text-dependent (TD) and text-independent (TI) speaker recognition models may be used. We wish to combine the advantages of both types of models through an ensemble system to make more reliable predictions. However, any such combined approach has to be robust to incomplete inputs, i.e., when either TD or TI input is missing. As a solution we propose a fusion of embeddings network foenet architecture, combining joint learning with neural attention. We compare foenet with four competitive baseline methods on a dataset of voice assistant inputs, and show that it achieves higher accuracy than the baseline and score fusion methods, especially in the presence of incomplete inputs.