LPC Features Research Articles

Unveiling personality traits through Bangla speech using Morlet wavelet transformation and BiG

Speech serves as a potent medium for expressing a wide array of psychologically significant attributes. While earlier research on deducing personality traits from user-generated speech predominantly focused on other languages, there is a noticeable absence of prior studies and datasets for automatically assessing user personalities from Bangla speech. In this paper, our objective is to bridge the research gap by generating speech samples, each imbued with distinct personality profiles. These personality impressions are subsequently linked to OCEAN (Openness, Conscientiousness, Extroversion, Agreeableness, and Neuroticism) personality traits. To gauge accuracy, human evaluators, unaware of the speaker’s identity, assess these five personality factors. The dataset is predominantly composed of around 90% content sourced from online Bangla newspapers, with the remaining 10% originating from renowned Bangla novels. We perform feature level fusion by combining MFCCs with LPC features to set MELP and MEWLP features. We introduce MoMF feature extraction method by transforming Morlet wavelet and fusing MFCCs feature. We develop two soft voting ensemble models, DistilRo (based on DistilBERT and RoBERTa) and BiG (based on Bi-LSTM and GRU), for personality classification in speech-to-text and speech modalities, respectively. The DistilRo model has gained F-1 score 89% in speech-to-text and the BiG model has gained F-1 score 90% in speech modality.

Text-to-Speech Synthesis for Hindi Language Using MFCC and LPC Feature Extraction Techniques

Text-to-Speech Synthesis for Hindi Language Using MFCC and LPC Feature Extraction Techniques

Pattern recognition and features selection for speech emotion recognition model using deep learning

Automatic speaker recognizing models consists of a foundation on building various models of speaker characterization, pattern analyzing and engineering. The effect of classification and feature selection methods for the speech emotion recognition is focused. The process of selecting the exact parameter in arrangement with the classifier is an important part of minimizing the difficulty of system computing. This process becomes essential particularly for the models which undergo deployment in real time scenario. In this paper, a new deep learning speech based recognition model is presented for automatically recognizes the speech words. The superiority of an input source, i.e. speech sound in this state has straight impact on a classifier correctness attaining process. The Berlin database consist around 500 demonstrations to media persons that is both male and female. On the applied dataset, the presented model achieves a maximum accuracy of 94.21%, 83.54%, 83.65% and 78.13% under MFCC, prosodic, LSP and LPC features. The presented model offered better recognition performance over the other methods.

A systematic approach for segmenting voiced/unvoiced signals using fuzzy-logic system and general fusion of neural network models for phonemes-based speech recognition

In this paper, a speech-to-text translation model has been developed for Malaysian speakers based on 41 classes of Phonemes. A simple data acquisition algorithm has been used to develop a MATLAB graphical user interface (GUI) for recording the isolated word speech signals from 35 non-native Malaysian speakers. The collected database consists of 86 words with 41 classes of phoneme based on Affricatives, Diphthongs, Fricatives, Liquid, Nasals, Semivowels and Glides, Stop and Vowels. The speech samples are preprocessed to eliminate the undesirable artifacts and the fuzzy voice classifier has been employed to classify the samples into voiced sequence and unvoiced sequence. The voiced sequences are divided into frame segments and for each frame, the Linear Predictive co-efficients features are obtained from the voiced sequence. Then the feature sets are formed by deriving the LPC features from all the extracted voiced sequences, and used for classification. The isolated words chosen based on the phonemes are associated with the extracted features to establish classification system input-output mapping. The data are then normalized and randomized to rearrange the values into definite range. The Multilayer Neural Network (MLNN) model has been developed with four combinations of input and hidden activation functions. The neural network models are trained with 60%, 70% and 80% of the total data samples. The neural network architecture was aimed at creating a robust model with 60%, 70%, and 80% of the feature set with 25 trials. The trained network model is validated by simulating the network with the remaining 40%, 30%, and 20% of the set. The reliability of trained network models were compared by measuring true-positive, false-negative, and network classification accuracy. The LPC features show better discrimination and the MLNN neural network models trained using the LPC spectral band features gives better recognition.

Speaker identification and its application in automobile industry for automatic seat adjustment

In this paper, an application of speaker identification in automobile industry is proposed. The work is divided into two main categories. The first part deals with the task of speaker identification where a system is trained and tested for multiple users using a database of isolated Hindi digits and Hindi sentences. A hybrid new algorithm is used for speaker identification which captures the benefits of both LPC and MFCC feature extraction technique. The new proposed technique shows an improvement of 2.05% over conventional MFCC features for isolated Hindi digits and 12.41% for Hindi sentences. It also shows an improvement of 53.26 over LPC for Hindi sentence and 32.51% for isolated Hindi digit over LPC. The proposed features were also tested for real time noisy environment by adding speech and F16 noise to test voice samples with varying degree of distortion starting from 0 to 20 dB. The second part describes the interfacing techniques and design of the hardware configuration for seat adjustment. The proposed model is designed using MATLAB. Speech samples from users are recorded through a microphone. Different features of this wav file are evaluated and fed into the model generated during testing phase. Depending on outcome from the classifier, a user is identified. Once the user is successfully identified, signals are sent to the servo motor through arduino microcontroller interfaced through MATLAB to automatically adjust the driver’s seat.

Isolated Word Recognition for Dysarthric Patients

In this paper, a HMM based speech recognition system is proposed for the Dysarthric patients. The speech samples recorded from patients with Spastic Dysarthria with mid to high intelligibility are taken from the UA Research database. The speech samples are de-noised using Discrete Wavelet Transform (DWT), after which the MFCC, LPC features are extracted. A comparative study on speech recognition using MFCC and LPC are presented. The recognition efficiency is found to be 68.50% using MFCC features and 66.54% using LPC features.

Speech coding using Best Tree Encoding (BTE) technique based on LPC and trigonometric features

Over the past several years there has been considerable attention focused on coding and enhancement of speech signals. This interest is progressed towards the development of new techniques capable of producing good quality speech at the output. Speech coding is a process of converting human speech into efficient encoded representations that can be decoded to produce a close approximation of the original signal. This paper deals with the problem of speech coding. It proposes novel approach called Best Tree Encoding (BTE) to encode the wavelet packet Best Tree Structure into a vector of four elements. This research is introducing BTE for solving another problem for speech compression and syntheses. Tree node data coefficients are encoded using LPC Filters and trigonometric features. The encoded vector consists of 4 elements from BTE analysis as well as LPC and trigonometric vector for each leaf node. The quality of the reproduced speech is evaluated for both understanding and quality. The quality of speech signal is measured on the basis of signal to noise ratio, log likelihood ratio, and spectral distortion.

Performance Analysis of MLP, Modified ERNN and TDNN on Telugu Command Recognition

In this paper, Telugu speech recognition is implemented using MLP and dynamic neural networks in MATLAB. Ten Telugu commands are the words of interest for recognition. Speech samples are collected for ten Telugu words from 30 different speakers in a noise free environment. Front end processing and LPC feature extraction are applied to raw speech data. Data is divided into training and testing sets. This paper gives different topologies of Artificial Neural Networks are used to investigate the Automated Speech Recognition of Telugu speech. The neural network topologies considered are MLP, Modified ERNN and TDNN. The word models are created by giving training data set as inputs to these networks and trained using backpropagation algorithm. Each neural network is trained to identify and classify the words into the respective word models. The testing data set is used to analyze the performance of the network.

Design and Development of Database and Automatic Speech Recognition System for Travel Purpose in Marathi

Past research in mathematics, acoustics, and speech technology have provided many methods for converting data that can be considered as information if interpreted correctly. In order to find some statistically relevant information from data, it is important to have mechanisms for reducing the information of each segment in the audio signal into features. These features should describe each segment in such a characteristic way that other similar segments can be grouped together by comparing their features. Preprocessing of speech signals is considered a crucial step in the development of a robust and efficient speech or speaker recognition system. This paper deals with result obtained by MFCC and LPC feature extraction technique and SVM feature matching technique.

Speech Recognition Error Compensation using MFCC and LPC Feature Extraction Method

Speech recognition system is input of inaccurate vocabulary by feature extraction case of recognition by appear result of unrecognized or similar phoneme recognized. Therefore, in this paper, we propose a speech recognition error correction method using phoneme similarity rate and reliability measures based on the characteristics of the phonemes. Phonemes similarity rate was phoneme of learning model obtained used MFCC and LPC feature extraction method, measured with reliability rate. Minimize the error to be unrecognized by measuring the rate of similar phonemes and reliability. Turned out to error speech in the process of speech recognition was error compensation performed. In this paper, the result of applying the proposed system showed a recognition rate of 98.3%, error compensation rate 95.5% in the speech recognition.

음소 유사율 오류 보정을 이용한 어휘 인식 후처리 시스템

어휘 인식 시스템에서 인식률 저하의 요인으로는 유사한 음소 인식과 부정확한 어휘 제공으로 인해 오인식 오류가 존재한다. 부정확한 어휘의 입력으로 특징을 추출하여 인식할 경우 오인식의 결과가 나타나거나 유사한 음소로 인식되며 특징 추출이 제대로 이루어지지 않으면 음소 인식 시 유사한 음소로 인식하게 된다. 따라서 본 논문에서는 음소가 갖는 특징을 기반으로 음소 유사율을 이용한 어휘 인식 후처리에서의 오류 보정 후처리 시스템을 제안하였다. 음소 유사율은 모노폰으로 훈련시킨 훈련 데이터를 각각의 음소에 MFCC와 LPC 특징 추출 방법을 이용하여 구하였다. 유사한 음소는 정확한 음소로 인식할 수 있도록 유도하여 부정확한 어휘 제공으로 인하여 오인식되는 오류를 최소화하였다. 음소 유사율과 신뢰도를 이용하여 오류 보정율을 구하였으며, 어휘 인식 과정에서 오류로 판명된 어휘에 대하여 오류 보정을 수행하였다. 에러패턴 학습을 이용한 시스템과 의미기반을 이용한 시스템에 비해 시스템 성능 평가 결과 MFCC와 LPC는 각각 7.5%와 5.3%의 인식 향상률을 보였다. In vocabulary recognition system has reduce recognition rate unrecognized error cause of similar phoneme recognition and due to provided inaccurate vocabulary. Input of inaccurate vocabulary by feature extraction case of recognition by appear result of unrecognized or similar phoneme recognized. Also can't feature extraction properly when phoneme recognition is similar phoneme recognition. In this paper propose vocabulary recognition post-process error correction system using phoneme likelihood based on phoneme feature. Phoneme likelihood is monophone training phoneme data by find out using MFCC and LPC feature extraction method. Similar phoneme is induced able to recognition of accurate phoneme due to inaccurate vocabulary provided unrecognized reduced error rate. Find out error correction using phoneme likelihood and confidence when vocabulary recognition perform error correction for error proved vocabulary. System performance comparison as a result of recognition improve represent MFCC 7.5%, LPC 5.3% by system using error pattern and system using semantic.

Study and evaluation of a multi-class SVM classifier using diminishing learning technique

Support vector machine (SVM) is one of the state-of-the-art tools for linear and non-linear pattern classification. One of the design objectives of an SVM classifier is reducing the number of support vectors without compromising the classification accuracy. For this purpose, a novel technique referred to as diminishing learning (DL) technique is proposed in this paper for a multiclass SVM classifier. In this technique, a sequential classifier is proposed wherein the classes which require stringent boundaries are tested one by one and once the tests for these classes fail, the stringency of the classifier is increasingly relaxed. An automated procedure is also proposed to obtain the optimum classification order for SVM–DL classifier in order to improve the recognition accuracy. The proposed technique is applied for SVM based isolated digit recognition system and is studied using speaker dependent and multispeaker dependent TI46 database of isolated digits. Both LPC and MFCC are used for feature extraction. The features extracted are mapped using self-organized feature maps (SOFM) for dimensionality reduction and the mapped features are used by SVM classifier to evaluate the recognition accuracy using various kernels. The performance of the system using the proposed SVM–DL classifier is compared with those using other techniques: one-against-all (OAA), half-against-half (HAH) and directed acyclic graph (DAG). SVM–DL classifier results in 1–2% increase in recognition accuracy compared to HAH classifier for some of the kernels with both LPC and MFCC feature inputs. For MFCC feature inputs, both HAH and SVM–DL classifiers have 100% recognition accuracy for some of the kernels. The total number of support vectors required is the least for HAH classifier followed by the SVM–DL classifier. The proposed diminishing learning technique is applicable for a number of pattern recognition applications.

Vowels recognition using mellin transform and plp-based feature extraction

Feature extraction for speech recognition is a subject of majer interest today. Different feature have been investigated in speech recognition systems. The scale transform is a particular restriction of the Mellin transform. The key property of the scale transform is the scale invariance.The mel frequency(MFCC) and perceptual linear predicate (PLP) have usually reported to have yielded good performance. In this paper, a new method is presented which combines feature extracted from mellin transform with the plp features. To evaluate the performance of the proposed features the comparative tests with the lpc features, MFCC and PLP were performed on the vowels based speech recognition system. Preliminary experiment show that this approach posses promissing result.

Hybrid wavelet based LPC features for Hindi speech recognition

Hybrid features are presented for speech recognition that uses linear prediction in combination with multi-resolution capabilities of wavelet transform. Wavelet-Based Linear Prediction Coefficients (WBLPC) are obtained by applying 3 and 4-level wavelet decomposition and then having linear prediction of each sub-bands to get total 13 features. These features have been tested using a linear discriminant function and Hidden Markov Model (HMM) based classifier for speaker dependent and independent isolated Hindi digits recognition. 3-level WBLPC features gave higher percentage recognition than LPC features while 4-level WBLPC features using HMM gave the highest percentage recognition for both speaker dependent and independent cases.

Experimental evaluation of features for robust speaker identification

This correspondence presents an experimental evaluation of different features and channel compensation techniques for robust speaker identification. The goal is to keep all processing and classification steps constant and to vary only the features and compensations used to allow a controlled comparison. A general, maximum-likelihood classifier based on Gaussian mixture densities is used as the classifier, and experiments are conducted on the King speech database, a conversational, telephone-speech database. The features examined are mel-frequency and linear-frequency filterbank cepstral coefficients, linear prediction cepstral coefficients, and perceptual linear prediction (PLP) cepstral coefficients. The channel compensation techniques examined are cepstral mean removal, RASTA processing, and a quadratic trend removal technique. It is shown for this database that performance differences between the basic features is small, and the major gains are due to the channel compensation techniques. The best "across-the-divide" recognition accuracy of 92% is obtained for both high-order LPC features and band-limited filterbank features.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

On the performance of isolated word speech recognizers using vector quantization and temporal energy contours

The technique of vector quantization has been widely applied in the area of speech coding and has recently been introduced into the area of speech recognition. For the conventional statistical pattern recognition word recognizer using LPC feature sets as the analysis frames, the use of vector quantization leads to a large reduction in computation for the dynamic time warping pattern matching, and a concomittant small increase in average word error rate. A second technique that has been recommended for improving the performance of isolated word recognizers is the addition of temporal energy information into the distance metric for comparing frames of speech. It has been shown that the information in the prosodic energy contour complements the segmental information of the LPC spectrum, thereby providing small but consistent improvements in performance for small word vocabularies. In this talk we present results of a series of speaker independent, isolated word recognition tests using a 10-word digits vocabulary and a 129-word airlines vocabulary. We show the effects, on recognition accuracy, of adding both vector quantization and temporal energy in various combinations, to the recognition paradigm.

On the effects of varying analysis parameters of an LPC based, isolated word recognizer

Speech recognition systems based on LPC features sets have been applied successfully to a number of speech recognition tasks including an airlines information system, a directory assistance system, a voice repertory dialer, and a connected digit recognizer. All these systems have been based on a recognition model, originally proposed by Itakura, with a fixed analysis parameter set. To get an appreciation for the robustness of this feature set, an experimental investigation was undertaken to vary each of the parameters of the analysis system, and to measure the effect of recognition accuracy. The parameters chosen for study included—N, the size of the analysis frame; L, the shift between frames; p the number of LPC poles; α, the preemphasis factor, and LP, the analog filter cutoff. Four talkers were used in this study. Each talker recited the vocabulary (the digits, the letters of the alphabet and three command words) seven times for training, and ten times for subsequent testing. The speech was stored in digital form at a sampling rate of 20 000 Hz. Speaker trained templates were obtained from the training data. The results of this study indicate that the recognition accuracy remained high over a wide range of variation of analysis parameters.