arXiv subjects

Hossein Sameti

Publications and source records attributed to Hossein Sameti.

23 records · Page 2Linked to original sources

arXiv2019

Replay Spoofing Countermeasure Using Autoencoder and Siamese Network on ASVspoof 2019 Challenge

Automatic Speaker Verification (ASV) is the process of identifying a person based on the voice presented to a system. Different synthetic approaches allow spoofing to deceive ASV systems (ASVs), whether using techniques to imitate a voice or recunstruct the features. Attackers try to beat up the ASVs using four general techniques; impersonation, speech synthesis, voice conversion, and replay. The last technique is considered as a common and high potential tool for spoofing purposes since replay attacks are more accessible and require no technical knowledge from adversaries. In this study, we introduce a novel replay spoofing countermeasure for ASVs. Accordingly, we used the Constant Q Cepstral Coefficient (CQCC) features fed into an autoencoder to attain more informative features and to consider the noise information of spoofed utterances for discrimination purpose. Finally, different configurations of the Siamese network were used for the first time in this context for classification. The experiments performed on ASVspoof challenge 2019 dataset using Equal Error Rate (EER) and Tandem Detection Cost Function (t-DCF) as evaluation metrics show that the proposed system improved the results over the baseline by 10.73% and 0.2344 in terms of EER and t-DCF, respectively.

eess.AS↗

arXiv2019

Speaker Recognition with Random Digit Strings Using Uncertainty Normalized HMM-based i-vectors

In this paper, we combine Hidden Markov Models (HMMs) with i-vector extractors to address the problem of text-dependent speaker recognition with random digit strings. We employ digit-specific HMMs to segment the utterances into digits, to perform frame alignment to HMM states and to extract Baum-Welch statistics. By making use of the natural partition of input features into digits, we train digit-specific i-vector extractors on top of each HMM and we extract well-localized i-vectors, each modelling merely the phonetic content corresponding to a single digit. We then examine ways to perform channel and uncertainty compensation, and we propose a novel method for using the uncertainty in the i-vector estimates. The experiments on RSR2015 part III show that the proposed method attains 1.52\% and 1.77\% Equal Error Rate (EER) for male and female respectively, outperforming state-of-the-art methods such as x-vectors, trained on vast amounts of data. Furthermore, these results are attained by a single system trained entirely on RSR2015, and by a simple score-normalized cosine distance. Moreover, we show that the omission of channel compensation yields only a minor degradation in performance, meaning that the system attains state-of-the-art results even without recordings from multiple handsets per speaker for training or enrolment. Similar conclusions are drawn from our experiments on the RedDots corpus, where the same method is evaluated on phrases. Finally, we report results with bottleneck features and show that further improvement is attained when fusing them with spectral features.

eess.AS↗

arXiv2018

Spoken Pass-Phrase Verification in the i-vector Space

The task of spoken pass-phrase verification is to decide whether a test utterance contains the same phrase as given enrollment utterances. Beside other applications, pass-phrase verification can complement an independent speaker verification subsystem in text-dependent speaker verification. It can also be used for liveness detection by verifying that the user is able to correctly respond to a randomly prompted phrase. In this paper, we build on our previous work on i-vector based text-dependent speaker verification, where we have shown that i-vectors extracted using phrase specific Hidden Markov Models (HMMs) or using Deep Neural Network (DNN) based bottle-neck (BN) features help to reject utterances with wrong pass-phrases. We apply the same i-vector extraction techniques to the stand-alone task of speaker-independent spoken pass-phrase classification and verification. The experiments on RSR2015 and RedDots databases show that very simple scoring techniques (e.g. cosine distance scoring) applied to such i-vectors can provide results superior to those previously published on the same data.

cs.SD↗

arXiv2017

SUT System Description for NIST SRE 2016

This paper describes the submission to fixed condition of NIST SRE 2016 by Sharif University of Technology (SUT) team. We provide a full description of the systems that were included in our submission. We start with an overview of the datasets that were used for training and development. It is followed by describing front-ends which contain different VAD and feature types. UBM and i-vector extractor training are the next details in this paper. As one of the important steps in system preparation, preconditioning the i-vectors are explained in more details. Then, we describe the classifier and score normalization methods. And finally, some results on SRE16 evaluation dataset are reported and analyzed.

cs.SD↗

arXiv2012

A Novel Method For Speech Segmentation Based On Speakers' Characteristics

Speech Segmentation is the process change point detection for partitioning an input audio stream into regions each of which corresponds to only one audio source or one speaker. One application of this system is in Speaker Diarization systems. There are several methods for speaker segmentation; however, most of the Speaker Diarization Systems use BIC-based Segmentation methods. The main goal of this paper is to propose a new method for speaker segmentation with higher speed than the current methods - e.g. BIC - and acceptable accuracy. Our proposed method is based on the pitch frequency of the speech. The accuracy of this method is similar to the accuracy of common speaker segmentation methods. However, its computation cost is much less than theirs. We show that our method is about 2.4 times faster than the BIC-based method, while the average accuracy of pitch-based method is slightly higher than that of the BIC-based method.

cs.AI↗