Zobrazeno 1 - 10
of 69
pro vyhledávání: '"Padmanabhan Rajan"'
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 30:1197-1206
Autor:
Akansha Tyagi, Padmanabhan Rajan
Publikováno v:
2022 30th European Signal Processing Conference (EUSIPCO).
Publikováno v:
Pattern Recognition Letters. 131:383-389
In this letter, we propose a concise feature representation framework for acoustic scene classification by pruning embeddings obtained from SoundNet, a deep convolutional neural network. We demonstrate that the feature maps generated at various layer
Publikováno v:
ICASSP
State-of-the-art spoken language identification (LID) networks are vulnerable to channel-mismatch that occurs due to the differences in the channels used to obtain the training and testing samples. The effect of channel-mismatch is severe when the tr
Autor:
Padmanabhan Rajan, Anshul Thakur
Publikováno v:
IEEE Journal of Selected Topics in Signal Processing. 13:298-309
We introduce a new classification framework that combines the characteristics of matrix factorization with the discriminative capabilities of kernel methods. Short-time analysis of audio signals having different durations result in sets of feature ve
Publikováno v:
SLT
State-of-the-art systems for spoken language identification (LID) use i-vector or embedding extracted using a deep neural network (DNN) to represent the utterance. These fixed-length representations are obtained without explicitly considering the rel
Oral presentation at "Exploring New Possibilities" 2022 Doctoral College Conference at University of Surrey, UK. An overview about the current work: Automated health monitoring of industrial machinery can help in avoiding unplanned downtime, increase
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::44a3d45406619e5a859f2615f045ba77
Publikováno v:
INTERSPEECH
Publikováno v:
The Journal of the Acoustical Society of America. 146(1)
Bioacoustic classification often suffers from the lack of labeled data. This hinders the effective utilization of state-of-the-art deep learning models in bioacoustics. To overcome this problem, the authors propose a deep metric learning-based framew
Publikováno v:
ICASSP
In this paper, we propose a statistical framework to prune feature maps in 1-D deep convolutional networks. SoundNet is a pre-trained deep convolutional network that accepts raw audio samples as input. The feature maps generated at various layers of