Speaker recognition using neural responses from the model of the auditory system

Razali, Noor Fadzilah; Jassim, Wissam A.; Roohisefat, Leyla; Zilany, Muhammad S. A.

doi:10.1109/ispacs.2014.7024428

Cited by 2 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was observed that the SI performance was, in general, not substantially different from each other for these window resolutions, although a slightly overall lower performance was seen when a window length of 7.6 ms was used (as shown in Table 1 for YOHO dataset). It is to be noted that the SI result shown in [ 27 ] using temporal fine structure (TFS) neurogram was higher compared to the performance using the low resolution envelope neurogram (as employed in this study). However, the results reported in that study was for the text-dependent SI system.…”

Section: Discussionmentioning

confidence: 60%

“…Universiti Malaya (UM) dataset is a text-dependent dataset and is an asset of the University of Malaya, Kuala Lumpur, Malaysia. This dataset has been collected for developing and testing the text-dependent speaker recognition systems [ 27 , 28 ]. In this dataset, speech samples have been collected from 39 Malaysian native speakers (25 males and 14 females) aged between 22 and 24 years.…”

Section: Methodsmentioning

confidence: 99%

“…The intelligibility scores predicted by NSIM and NOPM showed a good regression with the subjective scores for listeners with normal hearing and also for people with hearing loss under diverse background noise conditions such as with white Gaussian noise, speech-shaped noise and other environmental noises. Motivated by these results, a text-dependent speaker identification and verification systems were previously developed based on the responses of the model of the AN [ 27 , 28 ], and a substantial improvement in performance was achieved over conventional systems.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Robust Speaker Identification System Using the Responses from a Model of the Auditory Periphery

et al. 2016

Self Cite

View full text Add to dashboard Cite

Speaker identification under noisy conditions is one of the challenging topics in the field of speech processing applications. Motivated by the fact that the neural responses are robust against noise, this paper proposes a new speaker identification system using 2-D neurograms constructed from the responses of a physiologically-based computational model of the auditory periphery. The responses of auditory-nerve fibers for a wide range of characteristic frequency were simulated to speech signals to construct neurograms. The neurogram coefficients were trained using the well-known Gaussian mixture model-universal background model classification technique to generate an identity model for each speaker. In this study, three text-independent and one text-dependent speaker databases were employed to test the identification performance of the proposed method. Also, the robustness of the proposed method was investigated using speech signals distorted by three types of noise such as the white Gaussian, pink, and street noises with different signal-to-noise ratios. The identification results of the proposed neural-response-based method were compared to the performances of the traditional speaker identification methods using features such as the Mel-frequency cepstral coefficients, Gamma-tone frequency cepstral coefficients and frequency domain linear prediction. Although the classification accuracy achieved by the proposed method was comparable to the performance of those traditional techniques in quiet, the new feature was found to provide lower error rates of classification under noisy environments.

show abstract

Section: Discussionmentioning

confidence: 60%

Section: Methodsmentioning

confidence: 99%