Hanan Rosenthal - Academia.edu (original) (raw)

Uploads

Papers by Hanan Rosenthal

Deep learning, especially in the form of convolutional neu-ral networks (CNNs), has triggered sub... more Deep learning, especially in the form of convolutional neu-ral networks (CNNs), has triggered substantial improvements in computer vision and related fields in recent years. This progress is attributed to the shift from designing features and subsequent individual subsystems towards learning features and recognition systems end to end from nearly unprocessed data. For speaker clustering, however, it is still common to use handcrafted processing chains such as MFCC features and GMM-based models. In this paper, we use simple spectro-grams as input to a CNN and study the optimal design of those networks for speaker identification and clustering. Furthermore , we elaborate on the question how to transfer a network, trained for speaker identification, to speaker clustering. We demonstrate our approach on the well known TIMIT dataset, achieving results comparable with the state of the art– without the need for handcrafted features.

Deep learning, especially in the form of convolutional neu-ral networks (CNNs), has triggered sub... more Deep learning, especially in the form of convolutional neu-ral networks (CNNs), has triggered substantial improvements in computer vision and related fields in recent years. This progress is attributed to the shift from designing features and subsequent individual subsystems towards learning features and recognition systems end to end from nearly unprocessed data. For speaker clustering, however, it is still common to use handcrafted processing chains such as MFCC features and GMM-based models. In this paper, we use simple spectro-grams as input to a CNN and study the optimal design of those networks for speaker identification and clustering. Furthermore , we elaborate on the question how to transfer a network, trained for speaker identification, to speaker clustering. We demonstrate our approach on the well known TIMIT dataset, achieving results comparable with the state of the art– without the need for handcrafted features.

Log In