Search Results for author:
Found 2 papers, 0 papers with code
Generation of Speaker Representations Using Heterogeneous Training Batch Assembly
In traditional speaker diarization systems, a well-trained speaker model is a key component to extract representations from consecutive and partially overlapping segments in a long speech session.
Chain-based Discriminative Autoencoders for Speech Recognition
For application to robust speech recognition, we further extend c-DcAE to hierarchical and parallel structures, resulting in hc-DcAE and pc-DcAE.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
