Speech classification using SIFT features on spectrogram images

Nguyen, Quang Trung

doi:10.1007/s40595-016-0071-3

Cited by 19 publications

(5 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many speech applications like emotion classification [36][37][38][39][40][41][42], speech classification [43], sound event classification [44,45], speaker recognition [46,47], acoustic scene classification [48] use spectrograms as inputs to derive secondary features. SIFT features extracted from spectrograms are used for speech classification to perform speech classification [43]. Ren et al [44] extracted local binary pattern (LBP) from the logarithm of the Gammatone like spectrogram to do sound event classification.…”

Section: Discriminative Featuresmentioning

confidence: 99%

Classification of Pitch and Gender of Speakers for Forensic Speaker Recognition from Disguised Voices Using Novel Features Learned by Deep Convolutional Neural Networks

Nair¹,

Savithri²

2021

View full text Add to dashboard Cite

Voice disguise is a major concern in forensic automatic speaker recognition (FASR). Classifying the type of disguise is very important for speaker recognition. Pitch disguise is a very common type of disguise that criminals try to attempt. Among the different types of disguises, high pitch and low pitch voices show more distortion. The features that are robust for high pitch and low pitch voices are different. Moreover, the effect of disguise on male and female voices are also different. In this work, we classified high pitch and low pitch disguised voices for male and female voices using a novel set of features. We arranged Mel frequency cepstral coefficients (MFCC), ΔMFCC, and ΔΔMFCC features as three-dimensional features, and these are given as the RGB equivalent spectrogram inputs to pretrained AlexNet deep convolutional neural network (DCNN). We fused the AlexNet output features with corresponding MFCC correlation features. These fused features are the proposed novel features for disguise classification. Classification using neural network (NN) and support vector machine (SVM) classifiers are performed. Simulation results show that classification with SVM classifier using these novel features gives improved accuracy of 98.89% compared to 95.99% accuracy obtained by using DCNN output features using traditional spectrogram inputs.

show abstract

Section: Discriminative Featuresmentioning

confidence: 99%

Classification of Pitch and Gender of Speakers for Forensic Speaker Recognition from Disguised Voices Using Novel Features Learned by Deep Convolutional Neural Networks

Nair¹,

Savithri²

2021

View full text Add to dashboard Cite

show abstract

“…They are nowadays widely used as features in image/audio classification and separation systems [44], [45]. When tested on a sound event or speech classification task, they have shown to provide a significant improvement in classification performance when supplemented with other traditional audio features such as MFCCs and LPCCs [46], [47]. In this paper, we obtain the spectrum of an audio signal by calculating the short-time Fourier transform (STFT) of the audio input.…”

Section: ) Spectrogrammentioning

confidence: 99%

Toward Robust Audio Spoofing Detection: A Detailed Comparison of Traditional and Learned Features

et al. 2019

View full text Add to dashboard Cite

Automatic speaker verification, like every other biometric system, is vulnerable to spoofing attacks. Using only a few minutes of recorded voice of a genuine client of a speaker verification system, attackers can develop a variety of spoofing attacks that might trick such systems. Detecting these attacks using the audio cues present in the recordings is an important challenge. Most existing spoofing detection systems depend on knowing the used spoofing technique. With this research, we aim at overcoming this limitation, by examining robust audio features, both traditional and those learned through an autoencoder, that are generalizable to different types of replay spoofing. Furthermore, we provide a detailed account of all the steps necessary in setting up state-of-the-art audio feature detection, pre-, and postprocessing, such that the (non-audio expert) machine learning researcher can implement such systems. Finally, we evaluate the performance of our robust replay spoofing detection system with a wide variety and different combinations of both extracted and machine learned audio features on the 'out in the wild' ASVspoof 2017 dataset. This dataset contains a variety of new replay spoofing configurations. Since our focus is on examining which features will ensure robustness, we base our system on a traditional Gaussian Mixture Model-Universal Background Model (GMM-UBM). We then systematically investigate the relative contribution of each feature set. The fused models, based on both the known audio features and the machine learned features respectively, have a comparable performance with an Equal Error Rate (EER) of 12. The final best performing model, which obtains an EER of 10.8, is a hybrid system that contains both known and machine learned features, and is trained on an augmented dataset, thus revealing the importance of incorporating both types of features when developing a robust spoofing prediction model.

show abstract

“…Then, features were extracted from these broad phonetic categories and features were the input of back propagation neural network (BPNN) for classification. Gaussian mixture models (GMMs) have been also regarded as the most powerful model for estimating the probabilistic distribution of speech signals associated with each of these HMM states [4]. Meanwhile, the generative training methods of GMM-HMMs based on the expectation maximization (EM) algorithm have been considered for speech recognition [5].…”

Section: Introductionmentioning

confidence: 99%

Convolution neural networks with hybrid feature extraction methods for classification of voice sound signals

Rashmi¹,

Singh²

2023

World J. Adv. Eng. Technol. Sci.

View full text Add to dashboard Cite

The convolutional neural networks (CNNs) lead in the domain of Sound Recognition due to its flexibility and ability with different adjusting parameters. The recognition of spoken English Alphabets by different people with deep learning techniques attracted the research community. In this paper, we are exploring the use of convolutional neural network (CNN), a deep learner that can automatically learn features directly from the dataset while training for the classification of sounds signals of English alphabets. In this proposed work, we consider two CNN architectures. In first architecture, we propose MFCC based features for pretrained two convolutional layer CNN architecture. In the second architecture, we propose a hybrid feature extraction method to train a block-based CNN architecture. The proposed systems consist of two components namely hybrid feature extraction and CNN classifier. The five auditory features log-Mel spectrogram (LM), MFCC, chroma, spectral contrast and Tonnetz features are extracted and then LM & MFCC are combined as one feature set. LM, MFCC, and CST features are aggregated as another for training to the proposed two CNNs, respectively. The different sound samples of English alphabets are collected from different people of different age groups. The feature sets collected from the hybrid feature extraction methods are presented to both the proposed CNNs and the experimental results are collected. The experimental results indicate that the taxonomic accuracy of the proposed architectures can surpass the existing methods of CNNs with single feature extraction methods. The proposed second architecture performs more effectively over the proposed first CNN architecture.

show abstract

Speech classification using SIFT features on spectrogram images

Cited by 19 publications

References 38 publications

Classification of Pitch and Gender of Speakers for Forensic Speaker Recognition from Disguised Voices Using Novel Features Learned by Deep Convolutional Neural Networks

Classification of Pitch and Gender of Speakers for Forensic Speaker Recognition from Disguised Voices Using Novel Features Learned by Deep Convolutional Neural Networks

Toward Robust Audio Spoofing Detection: A Detailed Comparison of Traditional and Learned Features

Convolution neural networks with hybrid feature extraction methods for classification of voice sound signals

Contact Info

Product

Resources

About