Noise Robust ASV Spoof Detection Using Integrated Features and Time Delay Neural Network

Chakravarty, Nidhi; Dua, Mohit

doi:10.1007/s42979-022-01557-4

Cited by 16 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Malik et.al. [21], represented replay attacks as a nonlinear process and proposed the ATP-GTCC [35] combination to detect the harmonic distortions. The suggested ATP-GTCC feature space is used to train a multi-class SVM classifier, and tested for audio replay attack detection using the ECOC model.…”

Section: A Related Workmentioning

confidence: 99%

Spoof Detection using Sequentially Integrated Image and Audio Features

Chakravarty¹,

Dua²

2023

IJCDS

View full text Add to dashboard Cite

Analyzing the intricate nature of an audio signal often requires the extraction of relevant features, which serve as informative descriptors of the signal. It entails studying the signal and determining how signals are related to one another. As a result, the performance of audio spoofing detection in Automatic Speaker Verification (ASV) systems is strongly reliant on front-end feature extraction. In this paper, three types of successively integrated features have been proposed. First, Acoustic Ternary Pattern (ATP) image features are sequentially fused with different audio features such as MFCC, CQCC, GTCC, BFCC and PLP, individually. Second, LBP image features are combined with all these audio features similarly. Then, the sequential integration of ATP-LBP features is combined individually with MFCC, CQCC, GTCC, BFCC and PLP features. Finally, these front-end hybrid feature sets are classified using different ML and deep learning algorithms based acoustic models at the back-end. The state-of-the-art ASVspoof 2019 dataset has been used to implement various front-end and back-end combinations. The research outcomes reveal that the proposed approach achieved the best results with ATP-LBP-GTCC at the front end with LSTM-based acoustic model at the back-end.

show abstract

Section: A Related Workmentioning

confidence: 99%

Spoof Detection using Sequentially Integrated Image and Audio Features

Chakravarty¹,

Dua²

2023

IJCDS

View full text Add to dashboard Cite

show abstract

“…MFCC [14], Perceptual Linear prediction (PLP) [15], and Linear Frequency Cepstral Coefficient (LFCC) [16] feature extraction techniques have remained popular among past researchers. However, in recent years, Gammatone Cepstral Coefficients (GTCC) [17,18] feature extraction technique have become popular due to its noise robustness feature. Also, in last few years, it has been shown by various researchers that use of hybrid or integrated features have improved the performance of the ASV systems to a great extent.…”

Section: Introductionmentioning

confidence: 99%

Data augmentation and hybrid feature amalgamation to detect audio deep fake attacks

Chakravarty

Dua

2023

Phys. Scr.

View full text Add to dashboard Cite

The ability to distinguish between authentic and fake audio is become increasingly difficult due to the increasing accuracy of text-to-speech models, posing a serious threat to speaker verification systems. Furthermore, audio deepfakes are becoming a more likely source of deception with the development of sophisticated methods for producing synthetic voice. The ASVspoof dataset has recently been used extensively in research on the detection of audio deep fakes, together with a variety of machine and deep learning methods. The proposed work in this paper combines data augmentation techniques with hybrid feature extraction method at front-end. Two variants of audio augmentation method and Synthetic Minority Over Sampling Technique (SMOTE) have been used, which have been combined individually with Mel Frequency Cepstral Coefficients (MFCC), Gammatone Cepstral Coefficients (GTCC) and hybrid these two feature extraction methods for implementing front-end feature extraction. To implement the back-end our proposed work two deep learning models, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), and two Machine Learning (ML) classifier Random Forest (RF) and Support Vector Machine (SVM) have been used. For training, and evaluation ASVspoof 2019 Logical Access (LA) partition, and for testing of the said systems, and ASVspoof 2021 deep fake partition have been used. After analysing the results, it can be observed that combination of MFCC+GTCC with SMOTE at front-end and LSTM at back-end has outperformed all other models with 99% test accuracy, and 1.6 % Equal Error Rate (EER) over deepfake partition. Also, the testing of this best combination has been done on DEepfake CROss-lingual (DECRO) dataset. To access the effectiveness of proposed model under noisy scenarios, we have analysed our best model under noisy condition by adding Babble Noise, Street Noise and Car Noise to test data.

show abstract

“…The proposed research focuses on constructing an Automatic Speech Recognition (ASR) system for the Gujarati language using publicly accessible datasets. It employs a combination of MFCC and CQCC based integrated front-end feature extraction methodologies [4,5], as well as Bidirectional Encoder Representations from Transformers (BERT)-based improved spell corrector algorithm and Gated Recurrent Units (GRU)-based DeepSpeech2 model architecture [6,7]. In comparison to a model without post-processing, the results of the proposed work demonstrate a significant improvement in Word Error Rate (WER).…”

Section: Introductionmentioning

confidence: 99%

Enhancing Performance of End-to-End Gujarati Language ASR using combination of Integrated Feature Extraction and Improved Spell Corrector Algorithm

Bhagat

Dua

2023

ITM Web Conf.

View full text Add to dashboard Cite

A number of intricate deep learning architectures for effective End-to-End (E2E) speech recognition systems have emerged due to recent advancements in algorithms and technical resources. The proposed work develops an ASR system for the publicly accessible dataset on Gujarati language. The approach provided in this research combines features like Mel frequency Cepstral Coefficients (MFCC) and Constant Q Cepstral Coefficients (CQCC) at front-end feature extraction methodologies. Enhanced spell corrector with BERT-based algorithm and Gated Recurrent Units (GRU) based DeepSpeech2 architecture are used to implement the back end portion of the proposed ASR system. The proposed study shown that combining the MFCC features and CQCC features extracted from speech with the GRU-based DeepSpeech2 model and the upgraded or enhanced spell corrector improves the Word Error Rate (WER) by 17.46% when compared to the model without post processing.

show abstract

Noise Robust ASV Spoof Detection Using Integrated Features and Time Delay Neural Network

Cited by 16 publications

References 28 publications

Spoof Detection using Sequentially Integrated Image and Audio Features

Spoof Detection using Sequentially Integrated Image and Audio Features

Data augmentation and hybrid feature amalgamation to detect audio deep fake attacks

Enhancing Performance of End-to-End Gujarati Language ASR using combination of Integrated Feature Extraction and Improved Spell Corrector Algorithm

Contact Info

Product

Resources

About