Text Dependent Voice Recognition System using MFCC and VQ for Security Applications

This paper addresses the development of an Automatic Speech Recognition (ASR) system for the Moroccan Dialect. Dialectal Arabic (DA) refers to the day-to-day vernaculars spoken in the Arab world. In fact, Moroccan Dialect is very different from the Modern Standard Arabic (MSA) because it is highly influenced by the French Language. It is observed throughout all Arab countries that standard Arabic widely written and used for official speech, news papers, public administration and school but not used in everyday conversation and dialect is widely spoken in everyday life but almost never written. we propose to use the Mel Frequency Cepstral Coefficient (MFCC) features to specify the best speaker identification system. The extracted speech features are quantized to a number of centroids using vector quantization algorithm. These centroids constitute the codebook of that speaker. MFCC’s are calculated in training phase and again in testing phase. Speakers uttered same words once in a training session and once in a testing session later. The Euclidean distance between the MFCC’s of each speaker in training phase to the centroids of individual speaker in testing phase is measured and the speaker is identified according to the minimum Euclidean distance. The code is developed in the MATLAB environment and performs the identification satisfactorily.

Prior studies in the automatic classification of voice quality have mainly studied the use of the acoustic speech signal as input. Recently, a few studies have been carried out by jointly using both speech and neck surface accelerometer (NSA) signals as inputs, and by extracting mel-frequency cepstral coefficients (MFCCs) and glottal source features. This study examines simultaneously-recorded speech and NSA signals in the classification of voice quality (breathy, modal, and pressed) using features derived from three self-supervised pre-trained models (wav2vec2-BASE, wav2vec2-LARGE, and HuBERT) and using a support vector machine (SVM) as well as convolutional neural networks (CNNs) as classifiers. Furthermore, the effectiveness of the pre-trained models is compared in feature extraction between glottal source waveforms and raw signal waveforms for both speech and NSA inputs. Using two signal processing methods (quasi-closed phase (QCP) glottal inverse filtering and zero frequency filtering (ZFF)), glottal source waveforms are estimated from both speech and NSA signals. The study has three main goals: (1) to study whether features derived from pre-trained models improve classification accuracy compared to conventional features (spectrogram, mel-spectrogram, MFCCs, i-vector, and x-vector), (2) to investigate which of the two modalities (speech vs. NSA) is more effective as input in the classification task with pre-trained model-based features, and (3) to evaluate whether the deep learning-based CNN classifier can enhance the classification accuracy in comparison to the SVM classifier. The results revealed that the use of the NSA input showed better classification performance compared to the speech signal. Between the features, the pre-trained model-based features showed better classification accuracies, both for speech and NSA inputs compared to the conventional features. The two classifiers performed equally well for all the pre-trained model-based features for both speech and NSA signals. It was also found that the HuBERT features performed better than the wav2vec2-BASE and wav2vec2-LARGE features for both speech and NSA inputs. In particular, when compared to the conventional features, the HuBERT features showed an absolute accuracy improvement of 3%–6% for speech and NSA signals in the classification of voice quality.

Objective To investigate the feasibility of speech recognition technologies including double threshold method, Mel frequency cepstral coefficient (MFCC) and vector quantization (VQ) in automatic recognition of cough sounds. Methods Five healthy adults and 15 patients with cough were recruited for recording of both non- cough and cough sounds in a quiet environment. The records were randomized into training and testing samples. The training samples were used to generate the code book for cough recognition software, which was then used to recognize and analyze the testing samples automatically.The sensitivity and specificity of recognition were calculated by comparison with outcomes from human ear recognition. The recognition time in two approaches was recorded. Results Two hundred cough and 200 noncough sound samples were used to generate the code book for cough recognition software, while 375 cough sound samples and 125 non-cough sound samples were used as the testing samples. The recognition time of the testing samples needed was 33 minutes and 18 seconds by human ear recognition vs 1 minute and 35seconds by code book-based automatic recognition. In addition, the sensitivity and specificity in code bookbased automatic recognition of the cough sound were 98.93% and 100% respectively. Conclusion The double threshold method based on VQ and MFCC appears feasible in automatic recognition of cough sounds. Key words: Cough; Speech recognition software; Pattern recognition, automatic; Sensitivity and specificity; Human ear recognition

This paper presents a convolutional neural network-based pathological voice detection system using speech and electroglottographic (EGG) signals. Speech signals have been popularly used to detect voice pathology. Recently, the EGG signals have drawn considerable attention from researchers in this field. They argued that the EGG signals could detect the vocal fold vibration more accurately than speech signals and hence can be considered more appropriate for voice pathology detection. This work investigates the effectiveness of the EGG and speech signals in detecting pathological voices using sustained vowel (“/a/”) samples collected from the Saarbrücken Voice Database (SVD). The Mel frequency cepstral coefficients (MFCCs) extracted from the speech and EGG samples are employed as discerning features for this investigation. The results show that the proposed system achieves a higher accuracy (more than 23%) in identifying dysphonic voices from healthy ones with speech signals.

Telugu is the standard language used to communicate mainly in Andhra Pradesh and Telangana states with approximately 100 million speakers. Every Telugu word ends with vowels. Automatic speech recognition has major applications in the smart world. Telugu speech recognition has a huge scope of research from past decade. This paper deals with Telugu speech recognition in a speaker-dependent format for 10 words which are numbers from one to ten uttered by 10 speakers which creates a data base of 100 samples. Numbers are very frequently spoken words where recognition of these words plays a major role in Telugu speech recognition. These spoken words are preprocessed using various techniques like de-noising, framing, sampling, transformations, and endpoint detection. Methods like mel frequency cepstral coefficients (MFCC) and combined MFCC with modified group delay functions (MODGDF) are used for extracting the features. Extracted features are used for training and testing phase. Multilayer perceptron (MLP) and time lagged recurrent neural network (TLRN) patterns are trained and tested. Comparison is done for MLP and TLRN with the feature extraction techniques MFCC and MODGDF-MFCC. Integrated MODGDF-MFCC gives best accuracy in training and testing phases.

The aim of the study was to inspect the acoustic properties and sleep characteristics of a preapneic snoring sound. The feasibility of forecasting upcoming respiratory events by snoring sound was also investigated. Participants with habitual snoring or a heavy breathing sound during sleep were recruited consecutively. Polysomnography was conducted, and snoring-related breathing sound was recorded simultaneously. Acoustic features and sleep features were extracted from 30-second samples, and a machine learning algorithm was used to establish 2 prediction models. A total of 74 eligible participants were included. Model 1, tested by 5-fold cross-validation, achieved an accuracy of 0.92 and an area under the curve of 0.94 for respiratory event prediction. Model 2, with acoustic features and sleep information tested by Leave-One-Out cross-validation, had an accuracy of 0.78 and an area under the curve of 0.80. Sleep position was found to be the most important among all sleep features contributing to the performance of the 2 models. Preapneic sound presented unique acoustic characteristics, and snoring-related breathing sound could be deployed as a real-time apneic event predictor. The models, combined with sleep information, serve as a promising tool for an early warning system to forecast apneic events. Wang B, Yi X, Gao J, etal. Real-time prediction of upcoming respiratory events via machine learning using snoring sound signal. J Clin Sleep Med. 2021;17(9):1777-1784.

—The research on speech recognition systems currently focuses on the analysis of robust speech recognition systems. When the speech signals are combined with noise, the recognition system becomes distracted, struggling to identify the speech sounds. Therefore, the development of a robust speech recognition system continues to be carried out. The principle of a robust speech recognition system is to eliminate noise from the speech signals and restore the original information signals. In this paper, researchers conducted a frequency domain analysis on one stage of the Mel Frequency Cepstral Coefficients (MFCC) process, the Fast Fourier Transform (FFT), in children's speech recognition system. The FTT analysis in the feature extraction process determined the effect of frequency value characteristics utilized in the FFT output on the noise disruption. The analysis method was designed into three scenarios based on the value of the employed FFT points. The differences between scenarios were based on the number of shared FFT points. All FFT points were divided into four, three, and two parts in the first, second, and third scenarios, respectively. This study utilized children's speech data from the isolated TIDIGIT English digit corpus. As comparative data, the noise was added manually to simulate real-world conditions. The results showed that using a particular frequency portion following the scenario designed on MFCC affected the recognition system performance, which was relatively significant on the noisy speech data. The designed method in the scenario 3 (C1) version generated the highest accuracy, exceeded the accuracy of the conventional MFCC method. The average accuracy in the scenario 3 (C1) method increased by 1% more than all the tested noise types. Using various noise intensity values (SNR), the testing process indicates that scenario 3 (C1) generates a higher accuracy than conventional MFCC in all tested SNR values. It proves that the selection of specific frequency utilized in MFCC feature extraction significantly affects the recognition accuracy in a noisy speech.

This paper introduces a new approach to control and drive the DC motor, using speech recognition. The speech signal can be provided through microphone that is connected to computer. A DC motor connected through microcontroller can be driven in forward or reverse direction at different speeds, as well as it can be stopped by giving speech command. In this paper Mel Frequency Cepstral Co-efficient (MFCC) is used to recognize the user's speech and vector quantization is used to increase speech recognition accuracy. The MFCC and VQ algorithm, for speech recognition have been implemented in MATLAB 7.5 version on Windows Vista platform, and the supporting hardware setup is being implemented.

Significance of analytic phase of speech signals in speaker verification

The vast number of information packed into the human speech signal makes analysis a tough undertaking. This intricacy is notably noticeable in tasks like speaker recognition, especially when it comes to gender distinction. In this paper, we address this issue by conducting a thorough examination of the effectiveness of various speech features, namely Pitch, Formant Frequency, MFCC (Mel Frequency Cepstral Coefficients), and Chroma, in the context of gender identification in the Tai Language, which is spoken by the Tai people of Assam. In this study, we use machine learning (SVM, KNN, Decision Tree, Neural Network) to analyze speech features (Pitch, Formant Frequency, MFCC, Chroma) for gender identification in the Tai language spoken by the Tai people of Assam. Our results show that MFCC consistently outperforms other features, delivering the highest accuracy rates across all approaches. This demonstrates MFCC’s ability to extract gender information from Tai Language speech signals, suggesting more accurate gender identification systems. Beyond gender identification, our study extends voice analysis in linguistics and improves the application of spoken language data, allowing for improved communication systems and linguistic insights. In summary, our findings highlight the critical significance of MFCC in gender identification in the Tai language, with ramifications that extend far beyond its local context, promising advances in voice analysis and improving our understanding of language and human communication.

Automatic speech recognition (ASR) system is used to recognize the text transcript from the given speech signal. Such speech signal can contain either isolated words or large vocabulary continuous speech (LVCS). Isolated words can be recognized with high accuracy in clean environment, but recognizing continuous words involves various parameters like speech corpus, speaker, environment noise, etc., that affects the accuracy of automatic speech recognition system directly. In the proposed work, hybrid feature extraction technique combines the perceptual linear predictive (PLP) and mel frequency cepstral coefficient (MFCC) to improve the accuracy of ASR in noisy environment. Voice activity and detection (VAD)-based frame dropping is used for improving the phonemes modeling by removing the pauses and distorted elements from the given speech signal. The proposed hybrid model with VAD is implemented by using self-generated speech corpus and shows relatively 12% increase in recognition rate compared with the state-of-the-art methodology.KeywordsAutomatic speech recognition (ASR)Perceptual linear predictive (PLP)Mel frequency cepstral coefficient (MFCC)Voice activity and detection (VAC)

This paper presents significance of Mel-frequency Cepstral Coefficients (MFCC) Frequency band selection for text-independent speaker identification. Recent studies have been focused on speaker specific information that may extends beyond telephonic passband. The selection of the frequency band is an important factor to effectively capture the speaker specific information present in the speech signal for speaker recognition. This paper focuses on development of a speaker identification system based on MFCC features which are modeled using vector quantization. Here, the frequency band is varied up to 7.75 kHz. Speaker identification experiments evaluated on TIMIT database consisting of 630 speaker shows that the average recognition rate achieved is 97.37 % in frequency band 0–4.85 kHz for 20 MFCC filters.

Speaker recognition is a biometric technique which uses individual speakers voice samples as a input for recognition purpose. Main goal of this work is to obtain better accuracy for speaker recognition system for large number of voice database. In this paper, a comparative study is made between various combinations of features for speaker identification system with feedforward artificial neural network(FFANN) and support vector machine for 10 and 20 speakers. Linear predictive coding, Mel frequency cepstral coefficient and zero crossing rate are used as a feature extraction techniques. Each features are tested separately and in combination with FFANN and SVM classifier on Matlab software. For ANN classifier 70% of total database are used for training,15% for validation and remaining 15% data are used for testing, number of hidden layers and number of neurons used are 2 and 80 respectively. It is observed from the result that efficiency of the system is not dropping by increasing number of speakers from 10(320 voice samples) to 20(640 voice samples) when using combination of LPC, MFCC, ZCR features with ANN classifier.

This paper investigates the development of language identification based on Mel-Frequency Cepstral Coefficients (MFCC) and Vector Quantization (VQ) algorithm. In this study, a total of ten speakers were chosen randomly with different languages from online language database. A total of six males and four females were selected as subjects for this research and each of them spoke different languages, including Arabic, Chinese, English, Korean and Malay. The MFCC will be extracted to derive the related feature vector. Vector Quantization (VQ) algorithm is then used as classifier. The recognition rate is then calculated for each language. Several experiments were conducted to find the optimum parameters, in which we found that sampling frequency of 16000 Hz and codebook size of 75 provided good results. On average, the recognition rate for all five languages evaluated was 78%. The experimental results show that our proposed system provides a good recognition rate.

Speech signal processing has become an important mode of interaction with computer. In this paper, Mel Frequency Cepstral Coefficient (MFCC) technique has been used to process speech samples to attain the recognition. MFCC is a term which narrate the short-term power spectrum of a speech signal, depend on a linear cosine transform (FFT and DCT we have used in our work) of a log power spectrum on a nonlinear Mel scale of frequency. We have used Dynamic Time Warping algorithm and Cross Correlation algorithm to match feature vectors. We have taken five recorded reference word through “One” to “Five”. Then the feature vectors generated from this reference signals are stored in database. A test sample of any numeric in “One” to “Five” is again recorded and then the algorithm is applied to recognize the same with recorded reference voices. In our paper, the recognition techniques show different percentages of accuracy. The highest recognition accuracy we got 92% for Dynamic Time Warping algorithm with FFT transformation. The accuracy for Dynamic Time Warping algorithm using DCT is 86% which is less than DP algorithm using FFT. The average accuracy for Cross Correlation using FFT is 78% and average accuracy for DCT is only 60%.