Results 131 to 140 of about 598 (156)

Pseudo-color cochleagram image feature and sequential feature selection for robust acoustic event recognition

Applied Acoustics, 2018
This work proposes the use of pseudo-color cochleagram image of sound signals for feature extraction for robust acoustic event recognition. A cochleagram is a variation of the spectrogram. It utilizes a gammatone filter and has been shown to better reveal spectral information.
Roneel V Sharan, Tom J Moir
exaly   +5 more sources

Improving bottleneck features for automatic speech recognition using gammatone-based cochleagram and sparsity regularization

2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2015
Bottleneck (BN) features, particularly based on deep structures of a neural network, have been successfully applied to Automatic Speech Recognition (ASR) tasks. This paper goes on the study of improving the BN features for ASR tasks by employing two different methods: (1) a Cochleagram generated by Gammatone filters as the input feature for a deep ...
Jun Qi, Runsheng Liu
exaly   +2 more sources

Automatic Speech Emotion Recognition Using Cochleagram Features

Lecture Notes in Electrical Engineering, 2022
Jai Prakash Verma
exaly   +2 more sources

Ideal ratio mask estimation based on cochleagram for audio-visual monaural speech enhancement

Applied Acoustics, 2023
R Rajavel
exaly   +2 more sources

Cochleagram Based Speaker Identification Using Noise Adapted CNN

2021 5th International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), 2021
Nursadul Mamun, Azad Hossain
exaly   +2 more sources

Improved Speech Activity Detection Using Cochleagram Spectral Basis by Nonnegative Matrix Factorization

Lecture Notes in Electrical Engineering, 2022
Sujoy Mondal, Abhirup Das Barman
exaly   +2 more sources

Speaker-independent vowel recognition: spectrograms versus cochleagrams

International Conference on Acoustics, Speech, and Signal Processing, 2002
The ability of multilayer perceptrons (MLPs) trained with backpropagation to classify vowels excised from natural continuous speech is examined. Two spectral representations are compared: spectrograms and cochleagrams. The features used to train the MLPs include discrete Fourier transform (DFT) or cochleagram coefficients from a single frame in the ...
Yeshwant K. Muthusamy, Ronald A. Cole, Malcolm Slaney   +2 more
openaire   +1 more source

Detecting audio splicing forgery: A noise-robust approach with Swin Transformer and cochleagram

Journal of Information Security and Applications
Tolgahan Gülsoy, Elif Kanca, Arda Ustubioglu   +2 more
exaly   +2 more sources

CochleaTion: Speech Emotion Recognition Through Cochleagram with CNN-GRU and Attention Mechanism

2024 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT)
Khadija Akter
exaly   +2 more sources

Detection of tunnel lining voids using multi-channel cochleagram coefficients with an attention mechanism

Nondestructive Testing and Evaluation
Xiaobin Cheng, Zhaoli Yan
exaly   +2 more sources