A Hybrid GRU-CNN Feature Extraction Technique for Speaker Identification

Shihab, Md. Shazzad Hossain; Aditya, Shuvra; Setu, Jahangir Hossain; Imtiaz-Ud-Din, K. M.; Efat, Md. Iftekharul Alam

doi:10.1109/iccit51783.2020.9392734

Cited by 5 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these nonlinear features cannot be used as a stand-alone feature to achieve a performance that is anywhere close to what state-of-the-art techniques (using the linear feature) achieve. These recent techniques are based on deep learning architectures such as Convolutional Neural Networks (CNN) 24 , Wav2Vec2.0 25 , Deeper Feature CNN-Connectionist Temporal Classification (DFCNN-CTC) 26 , Gated Recurrence Unit-CNN (GRU-CNN) 27 etc.…”

Section: Nonlinear Dynamics Of Vocal Tract For Speaker Modelingmentioning

confidence: 99%

Recurrence plot embeddings as short segment nonlinear features for multimodal speaker identification using air, bone and throat microphones

Nawas,

Shahina,

Balachandar

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Speech is produced by a nonlinear, dynamical Vocal Tract (VT) system, and is transmitted through multiple (air, bone and skin conduction) modes, as captured by the air, bone and throat microphones respectively. Speaker specific characteristics that capture this nonlinearity are rarely used as stand-alone features for speaker modeling, and at best have been used in tandem with well known linear spectral features to produce tangible results. This paper proposes Recurrent Plot (RP) embeddings as stand-alone, non-linear speaker-discriminating features. Two datasets, the continuous multimodal TIMIT speech corpus and the consonant-vowel unimodal syllable dataset, are used in this study for conducting closed-set speaker identification experiments. Experiments with unimodal speaker recognition systems show that RP embeddings capture the nonlinear dynamics of the VT system which are unique to every speaker, in all the modes of speech. The Air (A), Bone (B) and Throat (T) microphone systems, trained purely on RP embeddings perform with an accuracy of 95.81%, 98.18% and 99.74%, respectively. Experiments using the joint feature space of combined RP embeddings for bimodal (A–T, A–B, B–T) and trimodal (A–B–T) systems show that the best trimodal system (99.84% accuracy) performs on par with trimodal systems using spectrogram (99.45%) and MFCC (99.98%). The 98.84% performance of the B–T bimodal system shows the efficacy of a speaker recognition system based entirely on alternate (bone and throat) speech, in the absence of the standard (air) speech. The results underscore the significance of the RP embedding, as a nonlinear feature representation of the dynamical VT system that can act independently for speaker recognition. It is envisaged that speech recognition too will benefit from this nonlinear feature.

show abstract

Section: Nonlinear Dynamics Of Vocal Tract For Speaker Modelingmentioning

confidence: 99%

Recurrence plot embeddings as short segment nonlinear features for multimodal speaker identification using air, bone and throat microphones

Nawas,

Shahina,

Balachandar

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Novel methods, algorithms, and more modern applications are currently being developed and improved for the segmentation of speech signals and the calculation of parametric indicators of selected fragments, thereby creating a spectrogram of speech signals using spectral analysis [ 4 , 5 , 6 , 7 ]. Speaker identification with diversified voice clips across the globe is a crucial and challenging task, especially in extracting vigorous and discriminative features [ 8 ]. A novel Mel Frequency Cepstral Coefficients (MFCC) feature extraction system that is quicker and more energy efficient than the traditional MFCC realization was proposed by Korkmaz et al [ 9 ].…”

Section: Related Workmentioning

confidence: 99%

Improved Feature Parameter Extraction from Speech Signals Using Machine Learning Algorithm

Abdusalomov

Safarov

Rakhimov

et al. 2022

Sensors

View full text Add to dashboard Cite

Speech recognition refers to the capability of software or hardware to receive a speech signal, identify the speaker’s features in the speech signal, and recognize the speaker thereafter. In general, the speech recognition process involves three main steps: acoustic processing, feature extraction, and classification/recognition. The purpose of feature extraction is to illustrate a speech signal using a predetermined number of signal components. This is because all information in the acoustic signal is excessively cumbersome to handle, and some information is irrelevant in the identification task. This study proposes a machine learning-based approach that performs feature parameter extraction from speech signals to improve the performance of speech recognition applications in real-time smart city environments. Moreover, the principle of mapping a block of main memory to the cache is used efficiently to reduce computing time. The block size of cache memory is a parameter that strongly affects the cache performance. In particular, the implementation of such processes in real-time systems requires a high computation speed. Processing speed plays an important role in speech recognition in real-time systems. It requires the use of modern technologies and fast algorithms that increase the acceleration in extracting the feature parameters from speech signals. Problems with overclocking during the digital processing of speech signals have yet to be completely resolved. The experimental results demonstrate that the proposed method successfully extracts the signal features and achieves seamless classification performance compared to other conventional speech recognition algorithms.

show abstract

A hybrid approach of Poisson distribution LDA with deep Siamese Bi-LSTM and GRU model for semantic similarity prediction for text data

Viji

Revathy

2023

Multimed Tools Appl

View full text Add to dashboard Cite

A Hybrid GRU-CNN Feature Extraction Technique for Speaker Identification

Cited by 5 publications

References 31 publications

Recurrence plot embeddings as short segment nonlinear features for multimodal speaker identification using air, bone and throat microphones

Recurrence plot embeddings as short segment nonlinear features for multimodal speaker identification using air, bone and throat microphones

Improved Feature Parameter Extraction from Speech Signals Using Machine Learning Algorithm

A hybrid approach of Poisson distribution LDA with deep Siamese Bi-LSTM and GRU model for semantic similarity prediction for text data

Contact Info

Product

Resources

About