User Identification System Using Biometrics Speaker Recognition by MFCC and DTW Along with Signal Processing Package

Muttaqi, Tazwar; Mousavinezhad, S. Hossein; Mahamud, Shaikh

doi:10.1109/eit.2018.8500256

Cited by 7 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, lecture will have highly similar windowed segments across various recordings. Since Mel Frequency Cepstral Coefficient (MFCC) has been widely used in the literature to compute similarity between audios [14,15,16], we extract MFCC from all of the audios that were recorded from the same class, and one recording is picked as a timing reference. The recording is started by a press of the button for each device, and the recording start time may differ by up to 10 minutes.…”

Section: Unsupervised Classification Of Lecture Versus Discussionmentioning

confidence: 99%

Unsupervised Methods for Audio Classification from Lecture Discussion Recordings

Dzodzo²,

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

Time allocated for lecturing and student discussions is an important indicator of classroom quality assessment. Automated classification of lecture and discussion recording segments can serve as an indicator of classroom activity in a flipped classroom setting. Segments of lecture are primarily the speech of the lecturer, while segments of discussion include student speech, silence and noise. Multiple audio recorders simultaneously document all class activities. Recordings are coarsely synchronized to a common start time. We note that the lecturer's speech tends to be common across recordings, but student discussions are captured only in the nearby device(s). Therefore, we window each recording at 0.5 s to 5 s duration and 0.1 s analysis rate. We compute the normalized similarity between a given window and temporally proximate window segments in other recordings. Histogram plot categorizes higher similarity windows as lecture and lower ones as discussion. To improve the classification performance, high energy lecture windows and windows with very high and very low similarity are used to train a supervised model, in order to regenerate the classification results of remaining windows. Experimental results show that binary classification accuracy improves from 96.84% to 97.37%.

show abstract

Section: Unsupervised Classification Of Lecture Versus Discussionmentioning

confidence: 99%

Unsupervised Methods for Audio Classification from Lecture Discussion Recordings

Dzodzo²,

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

show abstract

“…The results of the research may be generalized to a new finding that one efficient parameter (here the spectral slope) derived from a suitable subband of smoothed long-term spectrum is sufficient to successfully discriminate against speakers. When recognizing speakers and having long utterances available, the long-term speech spectrum can complement the traditional short-term voice features such as pitch [13], mel-frequency cepstral coefficients [11], line spectral pair frequencies [19], etc. and so help to improve recognition systems.…”

Section: Discussionmentioning

confidence: 99%

Speaker Discrimination Using Long-Term Spectrum of Speech

Sigmund

2019

ITC

View full text Add to dashboard Cite

In this article, we investigate a specific long-term speech spectrum with respect to its use for speaker recognition. The long-term effect was satisfied by averaging short-term autocorrelation coefficients over the whole utterance. The long-term spectrum was calculated by means of second-order linear prediction using the average autocorrelation coefficients. First, speaker discriminability of 32 individual parameters was evaluated by combining spectral energy and spectral slope in eight different frequency bands covering the range 0−4 kHz (seven narrow nonoverlapping subbands and one band spanning over the full range). Then, four subbands with the most discriminative capability were selected for speaker recognition. These subbands involve the frequencies of 0−1.2 kHz in total. In the main experiments, text-independent speaker recognition based on relative Euclidean distance was performed in each single subband as well as in multiple 2 to 4 subbands applying two types of speech data, complete continuous speech and voiced part of the same speech. The voiced speech seems to be generally more effective for speaker recognition using the long-term speech spectrum. The best recognition rates, i.e. 91.7% on complete speech and 100% on voiced speech, were achieved in optimal paired subbands. The long-term speech spectrum can complement the traditional voice features.

show abstract

“…Furthermore, [26] worked on a user identification system powered by biometrics speaker recognition using MFCC and Dynamic Time warping (DTW) alongside signal processing techniques. The aim of the author was to build a robust user identification system that uses precise voice recognition to increase data security and reduce to the barest minimum or possibly eliminate illicit access.…”

Section: Voice Recognition Systemmentioning

confidence: 99%

Voice Recognition Systems for The Disabled Electorate: Critical Review on Architectures and Authentication Strategies

et al. 2023

View full text Add to dashboard Cite

An inevitable factor that makes the concept of electronic voting irresistible is the fact that it offers the possibility of exceeding the manual voting process in terms of convenience, widespread participation, and consideration for People Living with Disabilities. The underlying voting technology and ballot design can determine the credibility of election results, influence how voters felt about their ability to exercise their right to vote, and their willingness to accept the legitimacy of electoral results. However, the adoption of e-voting systems has unveiled a new set of problems such as security threats, trust, and reliability of voting systems and the electoral process itself. This paper presents a critical literature review on concepts, architectures, and existing authentication strategies in voice recognition systems for the e-voting system for the disabled electorate. Consequently, in this paper, an intelligent yet secure scheme for electronic voting systems specifically for people living with disabilities is presented.

show abstract

User Identification System Using Biometrics Speaker Recognition by MFCC and DTW Along with Signal Processing Package

Cited by 7 publications

References 2 publications

Unsupervised Methods for Audio Classification from Lecture Discussion Recordings

Unsupervised Methods for Audio Classification from Lecture Discussion Recordings

Speaker Discrimination Using Long-Term Spectrum of Speech

Voice Recognition Systems for The Disabled Electorate: Critical Review on Architectures and Authentication Strategies

Contact Info

Product

Resources

About