Noise robust voice activity detection based on multi-layer feed-forward neural network
Yükleniyor...
Dosyalar
Tarih
2019
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Istanbul University
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
This paper proposes a voice activity detection (VAD) method based on time and spectral domain features using multi-layer feed-forward neural network (MLF-NN) for various noisy conditions. In the proposed method, time features that were short-time energy and zero-crossing rate and spectral features that were entropy, centroid, roll-off, and flux of speech signals were extracted. Clean speech signals were used in training MLF-NN and the network was tested for noisy speech at various noisy conditions. The proposed VAD method was evaluated for six kinds of noises which are white, car, babble, airport, street, and train at four different signal-to-noise ratio (SNR) levels. The proposed method was tested on core TIMIT database and its performance was compared with SOHN, G.729B and Long-Term Spectral Flatness (LSFM) VAD methods in point of correct speech rate, false alarm rate, and overall accuracy rate. Extensive simulation results show that the proposed method gives the most successful average correct speech rate, false alarm rate, and overall accuracy rate in most low and high SNR level conditions for different noise environments. © 2019 Istanbul University. All rights reserved.
Açıklama
Anahtar Kelimeler
Multi-layer feed-forward neural network, Time and spectral features, Voice activity detection, Errors, Feature extraction, Feedforward neural networks, Image resolution, Signal to noise ratio, Speech, Speech communication, Speech recognition, Extensive simulations, Multilayer feedforward neural networks, Noise environments, Overall accuracies, Short-time energy, Spectral feature, Voice activity detection, Zero crossing rate, Multilayer neural networks
Kaynak
Electrica
WoS Q Değeri
N/A
Scopus Q Değeri
Q3
Cilt
19
Sayı
2
