Isolated word language identification system with hybrid features from a deep belief network

Sangwan, Pardeep; Deshwal, Deepti; Kumar, Divya; Bhardwaj, Saurabh

doi:10.1002/dac.4418

Cited by 25 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning neural network model [4,9,13,14,15,20] is developed to perform LID. LID system is developed by using integration of MFCC with its shifted delta cepstrum as features and deep belief networks [5] for modeling and classi cation. Different sets of features [6, 8] are used for LID.…”

Section: Analysis Of Speech Uttered In Different Languagesmentioning

confidence: 99%

Real Time Raspberry Pi based System for Linguistic Content Recognition from Speech

2023

Preprint

View full text Add to dashboard Cite

Recognizing linguistic information from speech has found applications in interpretation of language in which the utterance is spoken and the system could be used as a translator to convert sentence spoken in one language into another language meaningfully. Real time implementation of language identification (LID) from speech requires the speech to be fed from the Raspberry Pi board used in the transmitter section and the Raspberry Pi board in the receiver section receives it and given to the system for identifying the language of the speech. This system requires the training phase in which two dimensional spectrogram features are derived from the training set of speeches and given to the CNN layered architecture for creating templates for languages. Testing phase involves the transmission of speech from the memory card of the Raspberry Pi board in transmitter system. Raspberry Pi board in the receiver receives it and given to the system in receiver section. Two dimensional spectrogram features are derived for test speech and given to the CNN templates and based on the similarity index, test language is interpreted. This system is implemented using spectrogram, Melspectrogram and ERB spectrogram as features and CNN for modeling and classification of languages. Validation error is 1.4%, 1.8% and 3% for spectrogram, Melspectrogram and ERB spectrogram based systems respectively and decision level fusion classifier gives 0.9% as validation error. This system can be implemented in hardware by using Raspberry Pi board. This automated real time multilingual language identification system would be useful in forensic department and defense sectors to identify the persons belonging to any region or speaking in any language.

show abstract

Section: Analysis Of Speech Uttered In Different Languagesmentioning

confidence: 99%

Real Time Raspberry Pi based System for Linguistic Content Recognition from Speech

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…• The device operation range for sub-threshold and super threshold regions is available. These devices can also be utilized as a biosensor as alternate methods are being explored in biomolecules detection for comparison and analysis of sensitivity to various devices [7,8]. These devices due to their high detection ability will help in improving the quality of medical tests and methods that can be utilized for mass usage.…”

Section: Introductionmentioning

confidence: 99%

Tunnelling FETs, the Non-conventional Transistors: Basics

Sheoran¹,

Shokeen²,

Sangwan³

et al. 2023

Proceedings of the 3rd International Conference on ICT for Digital, Smart, and Sustainable Development, ICIDSSD 2022, 24-25 Mar

View full text Add to dashboard Cite

The tunnel field-effect transistor (TFET) exploits the band to band tunneling (BTBT) phenomenon for carrier injection and this helps to lower the subthreshold swing <60mV/decade due to the absence of thermal (kT/q) dependence. Tunnel Field Effect Transistor has been evolved by T. Baba in 1992, and provides an alternative to conventional switch based on various performance parameters. TFETs show tremendous potential from the low-power applications point of view. However, the challenge to gain a high Ion/Ioff ratio in combination with subthreshold swing <60mV/decade still persists for devices to be used in high-performance circuits. To achieve this, it is required that many technologies to be used in combination for the realization of such hetero-structure TFET devices.

show abstract

“…There [22]. In these classification methods, the method with high accuracy often relies on a large number of data samples [23], which limits the data types that are difficult to obtain a large number of data and need to be quickly classified XGboost algorithm can quickly and accurately complete the construction of two-dimensional data classification model [24], and MFCC features can be transformed into two-dimensional matrix data through discrete cosine change [25]. Therefore, using XGboost to classify MFCC features has significant advantages.…”

Section: Introductionmentioning

confidence: 99%

Feature Classification Method of Frequency Cepstrum Coefficient Based On Weighted Extreme Gradient Boosting

Wang

Zhang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Cepstrum coefficient and decision tree classification provide a feasible method for mechanical fault diagnosis. However, this method has the problems of low accuracy of feature extraction and low reliability of feature classification. The efficiency and classification results of this method are not ideal. Therefore, this paper proposes a feature classification method of frequency cepstrum coefficients based on weighted extreme gradient boosting. The proposed method is mainly divided into two parts: feature extraction and feature classification. In the part of feature extraction, Considering the limitation of Mel frequency scale in MFCC, an adaptive frequency cepstrum coefficient (AFCC) method is proposed, which can adaptively obtain the frequency scale of the corresponding signal, thus improving the feature accuracy extracted by MFCC method. In the aspect of feature classification, XGboost algorithm has strong learning ability, which easily leads to over fitting and affects the classification accuracy, A weighted extreme gradient boosting (WXGB) method is proposed, and an improved distance evaluation method (IDE) is introduced to modify the feature weights learned by XGboost, so as to improve the prediction accuracy of the classification model. In order to verify the effectiveness of the method, the vibration signals of rolling bearings with different fault types are taken as samples to carry out feature extraction and classification. The results of feature extraction and classification of different methods are compared, and the effectiveness of the proposed feature classification method based on weighted extremum gradient boosting frequency cepstrum coefficient in rolling bearing fault diagnosis is verified.

show abstract

Isolated word language identification system with hybrid features from a deep belief network

Cited by 25 publications

References 21 publications

Real Time Raspberry Pi based System for Linguistic Content Recognition from Speech

Real Time Raspberry Pi based System for Linguistic Content Recognition from Speech

Tunnelling FETs, the Non-conventional Transistors: Basics

Feature Classification Method of Frequency Cepstrum Coefficient Based On Weighted Extreme Gradient Boosting

Contact Info

Product

Resources

About