Analyzing temporal properties of speech trajectory using graph structures towards speech recognition

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.

This paper reports some of the observations carried out on SUSE database for emotion classification. A comparative study is made to evaluate the performance of Linear Prediction Cepstral Coefficients (LPCCs) and Mel Frequency Cepstral Coefficients (MFCCs) for designing the emotion classification system for word level utterances. The significance of the orders of the coefficients has been carried out during this study. The results obtained using 12th order LPCC and 13th order MFCC are compared with respect to their reduced dimensions of lower orders. A new classification system based on the feature extraction technique using the 2nd, 3rd and 4th order coefficients of both MFCCs and LPCCs is also proposed. This paper compares the accuracy level of both MFCC and LPCC, enabling us to decide which orders of the parameters (both MFCC and LPCC) are more efficient in conveying the emotion for word level utterances. The initial experiments performed at word level utterances reveal that LPCC is more efficient in detecting emotion as compared to MFCC. Further, we noticed that the emotions conveyed in word level utterances are detected more accurately than that in sentence level utterances. The result suggests that word level approach provides better performance for emotion classification as compared to sentence level approach if the system is designed using vocal tract information only.

Speech recognition can be defined as the process of converting voice signals into the ranks of the word, by applying a specific algorithm that is implemented in a computer program. The research of speech recognition in Indonesia is relatively limited. This paper has studied methods of feature extraction which is the best among the Linear Predictive Coding (LPC) and Mel Frequency Cepstral Coefficients (MFCC) for speech recognition in Indonesian language. This is important because the method can produce a high accuracy for a particular language does not necessarily produce the same accuracy for other languages, considering every language has different characteristics. Thus this research hopefully can help further accelerate the use of automatic speech recognition for Indonesian language. There are two main processes in speech recognition, feature extraction and recognition. The method used for comparison feature extraction in this study is the LPC and MFCC, while the method of recognition using Hidden Markov Model (HMM). The test results showed that the LPC method is better than MFCC in Indonesian language speech recognition.

Chapter 10 - Parameterization techniques for automatic speech recognition system

The cry signals generated by infants serves as the primary communication for infants. Cry signals can provide insight into their wellbeing. This paper proposes to use the speech signal identification technique to recognize infant cry signals. Advanced signal processing methods are used to analyze the infant cry by using audio features in the time and frequency domains in an attempt to classify each cry to a specific need. The features extracted from audio feature space include linear predictive coding (LPC), linear predictive cepstral coefficients (LPCC), Bark frequency cepstral coefficients (BFCC) and Mel frequency cepstral coefficients (MFCC). The primary classification technique used were: nearest neighbor approach, neural networks method. The cry recognition of specific infants yielded promising results.

In this paper, we proposed a new set of speech feature parameters based on formant structure information. The speech signal is first divided into a gammatone filterbank, and then the Teager energy signal of each sub-band is extracted according to Teager Energy Operator. Two different energy separation algorithms, DESA-1 and DESA-2, are applied for obtain the instantaneous amplitude and frequency envelope of the formants, respectively. Finally, the feature vector is constructed by the amplitude and frequency information of the formants. The motivation of developing this new feature is that the formant location information is a quite distinct speech representation but seldom applied into speech recognition system before, and the conventional feature parameters such as mel-frequency cepstral coefficients (MFCC) and linear prediction cepstral coefficients (LPCC) do not explicitly model spectral peak information which is very important clue to identify the different phones. A Mandarin digit string recognition task is performed for evaluating the performance of the proposed feature parameter. The recognition results show an improved speech recognition performance compared to the conventional MFCC and LPCC.

Pattern classification models for classifying and indexing audio signals

Arabic language can be used by native and non- native speakers; due to Arabic is the language of the holy book of Muslims. In this paper, Arabic phoneme recognition system is proposed based on Malay speakers. This system consists of three main stages. The first stage is noise reduction and it aims to enhance the phoneme signals by excluding the unvoiced signals and keep only the voiced signal. Wiener filter is adapted to accomplish this task. The second stage is based on Mel-Frequency Cepstral Coefficients method to extract a vector of features to represent each phoneme signal. Eventually, pattern recognition neural network is designed as recognizer. The proposed system produces sufficient outcomes with 20 hidden neurons. Keywords—Arabic; Malay; pattern recognition; Wiener; Mel- Frequency Cepstral Coefficients I. INTRODUCTION It is well known the wide range of Artificial Neural Networks (ANN) application in speech recognition, financial, telecommunications, electronics and medical. As for speech recognition system for Arabic language, (1) & (2) have addressed the implementation of recognition system based on Arabic native speakers. In general, neural networks (NNs) for phonemes recognition are divided into several categories for instance Very Large Scale Integration (VLSI) NN that can be divided into digital and analogue with digital NNs being more compatible with feed-forward neural networks while analogue NNs are found to be more successful with recurrent NNs (3). From Automatic Speech System (ASR) point of view, NNs for recognition purpose can be divided into two main category namely conventional neural networks such as Multilayer Perceptron (MLP) and Radial Basis Function (RBF) and secondly Recurrent Neural Networks (RNN). The first category of NNs was implemented as pattern classifiers and proven capable for recognition purpose but not at par as compared to Hidden Markov Model (HMM) performance (2). At present, HMM has been proven to be the most successful approach in ASR research area until recently the possibility to hybrid both HMM and ANN (4) & (5). In general, speech recognition systems consist of three stages specifically noise reduction, feature extraction and classification. The aim of noise reduction is to reduce the level of noise in the speech signal and make it more compatible for the ASR. As for feature extraction, this process attempted to extract the most relevant features related to the phoneme signal. The extracted features acted as input features of the NN during training and testing. Finally, the purpose of classification process is to arrange the most similar and related features in categories based on the training phase. Basically, networks training database are being observed and updated during training session of the networks, involving the weights and biases arguments. Networks with lower errors can be considered as better networks (6). Hence, this paper deems to explore further the ability of NN for Arabic phonemes recognition spoken by Malay individuals. This paper is arranged as following; related work is discussed in section II followed by section III that discussed method to be implemented based on Wiener filter, Mel-Frequency Cepstral Coefficients and pattern recognition neural network. Section IV elaborated experimental analysis and results and followed by Conclusion section.

Emotional expressions are a fundamental aspect of human communication, with speech being one of the most natural modes of interaction. Speech Emotion Recognition (SER) is a significant research topic in Natural Language Processing (NLP), aimed at identifying emotions such as satisfaction, frustration, and anger from speech audio using multiple classifiers. This article presents a method to emotion recognition from spontaneous Tunisian Dialect (TD) speech, marking the first work in the SER field to utilize spontaneous speech for emotion recognition in this dialect. The dataset was created from freely available YouTube videos across multiple domains and labeled with four perceived emotions: anger, satisfaction, frustration, and neutral. To address the data scarcity issue, we implemented data augmentation techniques, specifically Vocal Tract Length Perturbation (VTLP). The preprocessing of the speech signals involved cleaning the data from ambient and unwanted noises. We extracted and selected various spectral features, including Mel-Frequency Cepstral Coefficients (MFCCs) and Linear Prediction Cepstral Coefficients (LPCC). Subsequently, we applied several classification methods: Support Vector Machine (SVM), Bidirectional Long Short-Term Memory (BiLSTM), Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Random Forest. Our experiments demonstrated that the Random Forest classifier achieved the highest F-score of 58.75%. The results were thoroughly discussed, analyzed, and compared across the five models using different feature extractions. This study provides valuable insights and advancements in the SER field, particularly for the TD, for future research directions for improving emotion recognition systems.

In this paper, a new set of features for addressing the problem of unsupervised query-by-example spoken term detection is proposed. The main purpose of this is to find a spoken query in large speech databases. In unsupervised audio search, language specific resources are not required. Thus this system is more appropriate in cases where enough training data is not available for creating an Automatic Speech Recognition(ASR). Current state-of-the-art techniques use Mel Frequency Cepstral Co-efficients(MFCC), Linear Predictive Cepstral Coefficients(LPCC) etc. as the features. For improving the performance of the system, Fourier Bessel Cepstral Coefficients(FBCC) is used in this paper. Here, from the spoken example of a keyword, segmental Dynamic Time Warping is used to compare the Gaussian Posteriorgrams, which are created from the FBCC feature vector. The keyword detection result obtained using MediaEval 2012 database shows that this system outperforms the one that uses MFCC alone due to the fact that Bessel features are more efficient for representing speech signals compared to MFCC.

A statistically designed Automatic Speech Recognition (ASR) system extracts features from speech signals using feature extraction methods, links the extracted features with the expected phonetics of the hypothesis using acoustic models, uses language model to add prior information about the structure of the target language. For many years, Mel-frequency Cepstral coefficients (MFCC), n-gram, and Hidden Markov Model (HMM) approaches have been used predominantly for feature extraction, language modeling and acoustic modeling, respectively. However, performance degradation of MFCC in noisy conditions and inaccuracy of HMMs while handling large vocabularies have made researchers to propose more efficient methods. The proposed work uses noise robust method Gammatone Frequency Cepstral Coefficients(GFCC) for feature extraction, trigram language modeling, and HMM-Gaussian mixture model (GMM) based acoustic modeling to implement a continuous Hindi language ASR system. Also, it applies Differential Evolution (DE) technique to refine the GFCC features and discriminative techniques to enhance performance of the acoustic model. The performance of the implemented system has been evaluated by using different feature extraction methods, variants of n-gram language modeling techniques and different discriminative techniques in clean as well as noisy conditions. Initially, the results reveal that DE optimized GFCC with HMM-Gaussian Mixture Model (GMM) acoustic modeling performs better than MFCC, PLP and MF-PLP feature extraction methods. Secondly, the experimental results show that the Minimum Phone Error (MPE) outperforms Maximum Mutual Information (MMI) and Maximum Likelihood Estimation (MLE) and trigram based language modeling gives more accurate results than unigram and bigram language modeling. Finally, it has been concluded that the continuous Hindi language ASR system implemented using DE refined GFFC feature extraction method with MPE discriminative training technique and trigram based language modeling gives better accuracy in clean as-well-as noisy environments.

It is very important to enhance the recognition accuracy of the Arabic spoken letters. The accuracy of recognition system is affected by the feature extraction and the used classifier. An effective and robust method is proposed to evaluate speech feature to improve the performance the recognition accuracy. This work introduces applying the mel frequency cepstral coefficient (MFCC) to extract the speech features. Hidden Markov model and neural network are used as classifier tools. The objective of the proposed system is to enhance the performance by introducing three systems which are proposed to recognize the spoken Arabic letters. The first is based on neural networks. The second is based on hidden Markov model. While third system is based on combination between neural networks and hidden Markov models. The accuracy of neural network is found to be 42% with MFCC for 84 spoken letters. The hidden Markov models are statistical based approach. Its performance is found to be 98.5%. But for combination system based on neural network and hidden Markov models, the accuracy of 99.25% is obtained.

The objective of speech emotion recognition (SER) is to enhance man-machine interface. It can also be used to cover the physiological state of a person in critical situations. In recent time, speech emotion recognition also finds its operations in medicine and forensics. A new feature extraction technique using Teager energy operator (TEO) is proposed for the detection of stressed emotions as Teager energy-autocorrelation envelope (TEO-Auto-Env). TEO is basically designed for increasing the energies of the stressed speech signals whose energies are reduced during the speech production process and hence used in this analysis. A stressed speech emotion recognition (SSER) system is developed using TEO-Auto-Env and spectral feature combination for detecting the emotions. The spectral features considered are Mel-frequency cepstral coefficients (MFCC), linear prediction cepstral coefficients (LPCC), and relative spectra-perceptual linear prediction (RASTA-PLP). EMO-DB (German), EMOVO (Italian), IITKGP (Telugu), and EMA (English) databases are used in this analysis. The classification of the emotions is carried out using the k-nearest neighborhood (k-NN) classifier for gender-dependent (GD) and speaker-independent (SI) cases. The proposed SSER system provides improved accuracy compared to the existing ones. Average recall is used for performance evaluation. The highest classification accuracy is achieved using the feature combination of TEO-Auto-Env, MFCC, and LPCC features with 91.4% (SI), 91.4% (GD-male), and 93.1%(GD-female) for EMO-DB; 68.5% (SI), 68.5% (GD-male), and 74.6% (GD-female) for EMOVO; 90.6%(SI), 91% (GD-male), and 92.3% (GD-female) for EMA; and 95.1% (GD-female) for IITKGP female database.

Tamil Language is one of the ancient Dravidian languages spoken in south India. Most of the Indian languages are syllabic in nature and syllables are in the form of Consonant-Vowel (CV) units. In Tamil language, CV pattern occurs in the beginning, middle and end of a word. In this work, CV units formed with Stop Consonant – Short Vowel (SCSV) were considered for classification task. The work carried out in three stages, Vowel Onset Point (VOP) detection, CV segmentation and classification. VOP is an event at which the consonant part ends and vowel part begins. VOPs are identified using linear Prediction residuals which provide significant characteristics of the excitation source. To segment the CV units, fixed length spectral frames before and after VOPs are considered. Both production based features - Linear Predictive Cepstral Coefficients (LPCC) and perception based features - Mel Frequency Cepstral Coefficients (MFCC) are extracted and given as input to the classifiers designed with multilayer perceptron and support vector machine. A speech corpus of 200 Tamil words uttered by 15 native speakers was used, which covers all SCSV units formed with Tamil stop consonants (/k/,/ch/,/d/,/t/,/p/) and short vowels (/a/,/i/, /u/, /e/, /o/). The classifiers are trained and tested for its performance using various measures. The results indicate that the model built with MFCC using support vector machine RBF kernel outperforms.

Drone classification using RF signal based spectral features