Isolated Word Speech Recognition Research Articles

Isolated Word Speech Recognition Using Mixed Transform

Methods of speech recognition have been the subject of several studies over the past decade. Speech recognition has been one of the most exciting areas of the signal processing. Mixed transform is a useful tool for speech signal processing; it is developed for its abilities of improvement in feature extraction. Speech recognition includes three important stages, preprocessing, feature extraction, and classification. Recognition accuracy is so affected by the features extraction stage; therefore different models of mixed transform for feature extraction were proposed. The properties of the recorded isolated word will be 1-D, which achieve the conversion of each 1-D word into a 2-D form. The second step of the word recognizer requires, the application of 2-D FFT, Radon transform, the 1-D IFFT,and 1-D discrete wavelet transforms were used in the first proposed model, while discrete multicircularlet transform was used in the second proposed model. The final stage of the proposed models includes the use of the dynamic time warping algorithm for recognition tasks. The performance of the proposed systems was evaluated using forty different isolated Arabic words that are recorded fifteen times in a studio for speaker dependant. The result shows recognition accuracy of (91% and 89%) using discrete wavelet transform type Daubechies (Db1) and (Db4) respectively, and the accuracy score between (87%-93%) was achieved usingdiscrete multicircularlet transform for 9 sub bands.

Analysis of Rehabilitation Occupational Therapy Techniques Based on Instrumental Music Chinese Tonal Language Spectrogram Analysis.

This paper provides an in-depth analysis of timbre-speech spectrograms in instrumental music, designs a model analysis of rehabilitation occupational therapy techniques based on the analysis of timbre-speech spectrograms in instrumental music, and tests the models for comparison. Starting from the mechanism of human articulation, this paper models the process of human expression as a time-varying linear system consisting of excitation, vocal tract, and radiation models. The system's overall architecture is designed according to the characteristics of Chinese speech and everyday speech rehabilitation theory (HSL theory). The dual judgment of temporal threshold and short-time average energy realized the phonetic length training. Tone and clear tone training were achieved by linear predictive coding technique (LPC) and autocorrelation function. Using the DTW technique, isolated word speech recognition was achieved by extracting Mel-scale Frequency Cepstral Coefficients (MFCC) parameters of speech signals. The system designs corresponding training scenes for each training module according to the extracted speech parameters, combines the multimedia speech spectrogram motion situation with the speech parameters, and finally presents the training content as a speech spectrogram, and evaluates the training results through human-machine interaction to stimulate the interest of rehabilitation therapy and realize the speech rehabilitation training of patients. After analyzing the pre- and post-test data, it was found that the p-values of all three groups were <0.05, which was judged to be significantly different. Also, all subjects changed their behavioral data during the treatment. Therefore, it was concluded that the music therapy technique could improve the patients' active gaze communication ability, verbal command ability, and active question-answering ability after summarizing the data, i.e., the hypothesis of this experiment is valid. Therefore, it is believed that the technique of timbre-speech spectrogram analysis in instrumental music can achieve the effect of rehabilitation therapy to a certain extent.

Practical Study and Implementation of an Isolated Word Speech Recognition System.(Dept.E)

The art and science of speech recognition have been advanced to the state where it is now possible to communicate reliably with a machine by speaking to it in a disciplined manner using a vocabulary of moderate size. It is the purpose of this paper to present a hardware implementation of a simple real time speech recognition system for isolated words. The system determines the energy of the spoken word through a bank of four channels band pass filters. The output from each filter is passed through a rectifier followed by a low pass filter to provide an average level which is proportional to the total signal energy within the particular filter band. The energy measurements from each channel is then passed to a personal computer where a recognition algorithm program is then executed. The program detects the starting and ending points of each spoken word. compares the energy features with the reference stored in the library, and chooses the most close pattern that matches the pattern of the spoken word. Results from experiments conducted by simulation and by the hardware prototype using Arabic speech show that the system provides recognition score between 76 % and 94%.

Phone based acoustic modeling for automatic speech recognition for Punjabi language

Punjabi language is a tonal language belonging to an Indo-Aryan language family and has a number of speakers all around the world. Punjabi language has gained acceptability in the media &amp; communication and therefore deserves to have a place in the growing field of automatic speech recognition which has been explored already for a number of other Indian and foreign languages successfully. Some work has been done in the field of isolated word speech recognition for Punjabi language, but only using whole word based acoustic models. A phone based approach has yet to be applied for Punjabi language speech recognition. This paper describes an automatic speech recognizer that recognizes isolated word speech and connected word speech using a triphone based acoustic model on the HTK 3.4.1 speech Engine and compares the performance with acoustic whole word model based ASR system. Word recognition accuracy of isolated word speech was 92.05% for acoustic whole word model based system and 97.14% for acoustic triphone model based system whereas word recognition accuracy of connected word speech was 87.75% for acoustic whole word model based system and 91.62% for acoustic triphone model based system.

Application of an Isolated Word Speech Recognition System in the Field of Mental Health Consultation: Development and Usability Study.

BackgroundSpeech recognition is a technology that enables machines to understand human language.ObjectiveIn this study, speech recognition of isolated words from a small vocabulary was applied to the field of mental health counseling.MethodsA software platform was used to establish a human-machine chat for psychological counselling. The software uses voice recognition technology to decode the user's voice information. The software system analyzes and processes the user's voice information according to many internal related databases, and then gives the user accurate feedback. For users who need psychological treatment, the system provides them with psychological education.ResultsThe speech recognition system included features such as speech extraction, endpoint detection, feature value extraction, training data, and speech recognition.ConclusionsThe Hidden Markov Model was adopted, based on multithread programming under a VC2005 compilation environment, to realize the parallel operation of the algorithm and improve the efficiency of speech recognition. After the design was completed, simulation debugging was performed in the laboratory. The experimental results showed that the designed program met the basic requirements of a speech recognition system.

Implementation of a Biometric Interface in Voice Controlled Wheelchairs

In order to assist physically handicapped persons in their movements, we developed an embedded isolated word speech recognition system (ASR) applied to voice control of smart wheelchairs. However, in spite of the existence in the industrial market of several kinds of electric wheelchairs, the problem remains the need to manually control this device by hand via joystick; which limits their use especially by people with severe disabilities. Thus, a significant number of disabled people cannot use a standard electric wheelchair or drive it with difficulty. The proposed solution is to use the voice to control and drive the wheelchair instead of classical joysticks. The intelligent chair is equipped with an obstacle detection system consisting of ultrasonic sensors, a moving navigation algorithm and a speech acquisition and recognition module for voice control embedded in a DSP card. The ASR architecture consists of two main modules. The first one is the speech parameterization module (features extraction) and the second module is the classifier which identifies the speech and generates the control word to motors power unit. The training and recognition phases are based on Hidden Markov Models (HMM), K-means, Baum-Welch and Viterbi algorithms. The database consists of 39 isolated speaker words (13 words pronounced 3 times under different environments and conditions). The simulations are tested under Matlab environment and the real-time implementation is performed by C language with code composer studio embedded in a TMS 320 C6416 DSP kit. The results and experiments obtained gave promising recognition ratio and accuracy around 99% in clean environment. However, the system accuracy decreases considerably in noisy environments, especially for SNR values below 5 dB (in street: 78%, in factory: 52%).

Audio Visual Technique for Enhancing the Isolated Word Speech Recognition System

This paper reports the enhancing of isolated word speech recognition system using audio visual features which are extracted from the context speech. Hand gestures captured which are co-expressive with speech are extracted from the context of speech. Both static and dynamic gestures are experimented as part of this study. The extracted gestural features are considered as augmenting features for improving the accuracy of isolated word speech recognition system. The performance of the system are measured under different noise conditions. The experimental results are tabulated under different signal to noise ratio conditions. Keywords: Speech Recognition, Multimodal, Gesture recognition, Audio Visual Techniques, Non-acoustic features

The Realization of a Speech-control Unit Used for Intelligent Household Appliance

This paper introduces a speech-control unit to control the switch of household appliance. The isolated word speech recognition system is designed by using the discrete Hidden Markov model (HMM) to train and recognize the model. According to the specific target of the speech-control unit, we introduce the two methods to realize the speech-control unit, and discuss some specific problems during its realization in C language. And in KEIL uVision5 software development environment, simulate and download the program to realize the intelligent household appliance system.

Simulation and Analysis of Isolated Word Speech Recognition

Simulation and Analysis of Isolated Word Speech Recognition

The Research of Speech Recognition in Low SNR Based on GA-SVM

To improve recognizing rate and recognizing efficiency, the algorithm of double-threshold is adopted in the endpoint detection, Mel-frequency Spectral Coefficients is obtained as speech characteristic parameters, the SVM parameters, penalty factor and kernel function parameter, were optimized with genetic algorithm, then, an speech recognition model was established with GA-SVM method. The improved algorithm was simulated by matlab, the experiment shows that this algorithm can achieved good results in isolated word speech recognition.

Isolated Word Speech Recognition System Based On FPGA

The paper introduces an isolated word speech recognition system in which the speech signal is acquired in real time. Half Raised-Sine function is applied to the MFCC parameters of the audio files, and improved DTW algorithm is implemented. Simulation results show that compared the conventional DTW with the improved DTW algorithm, the latter can obtain a better recognition rate and faster response time. Finally, the system was implemented on FPGA and yields satisfactory performance.

Optimization of MLP Using Genetic Algorithms Applied to Arabic Speech Recognition

This paper presents a novel system for Arabic speech recognition of Arabic isolated words with mono-locutor and a small vocabulary. We have used a database consisting of eleven isolated Arabic words each of them was repeated twenty five times by the same -locutor. Mel Frequency Cepstral Coefficient (MFCC) and Bionic Wavelet Transform (BWT) are used for feature extraction from each recorded word. The obtained coefficients were then concatenated to construct one input node of a Multi-Layer Perceptual (MLP) used for features classification and recognition. We describe in this paper the use of Genetic Algorithm (GA) for optimizing the topology of each Multi-Layer Perceptron (MLP). So, the GA is utilized to find the optimal number of neurons in input layer and in hidden layer, the training epochs and the learning goal of network. From the results, it was observed that the integration of the GA with feed forward network can improve classification rate to 100%

A Parameters Optimization Method of v-Support Vector Machine and Its Application in Speech Recognition

An important factor that influences the performance of support vector machine is how to select its parameters. In traditional C-support vector machine, it is difficult to select penalty parameter C and kernel parameters, inappropriate choice of those values may cause deterioration of its performance and increase algorithm complexity. In order to solve those problems, in this paper, selected v - support vector machine as the research object, proposed an optimal parameters search method for the Gaussian kernel v - support vector machine based on improved particle swarm optimization, constructed a non- specific person and isolated words speech recognition system based on v - support vector machine using the optimized parameters firstly. Experiments show that this new v - support vector machine method achieves better speech recognition correct rates than traditional C-support vector machine in different signal to noise ratios and different words, this new improved method of optimizing v - SVM parameters is very efficient and has shorter convergence time, and makes v - support vector machine have better Performance in speech recognition system.

Dialectal alarm words recognition based on a hybrid model of Hidden Markov Models and the BP Neural Network

This paper explores the small-vocabulary speaker-independent isolated-word speech recognition technology. A recognition system based on a hybrid model of Hidden Markov Model and BP Neural Network is constructed. The HMM is used for computing the Viterbi output score which is inputted into the BP network to acquire the classification information. A corpus with more than 2500 speech samples is created, which includes three dialects (mandarin, shannxi dialect, English), and each kind of dialect contains four alarm word (“help”, “hijack”, “murder”, fire”). Recognition experiments are carried out using the corpus. The results show that the hybrid model has higher performance than the hidden Markov model.

Dereverberation and denoising based on generalized spectral subtraction by multi-channel LMS algorithm using a small-scale microphone array

A blind dereverberation method based on power spectral subtraction (SS) using a multi-channel least mean squares algorithm was previously proposed to suppress the reverberant speech without additive noise. The results of isolated word speech recognition experiments showed that this method achieved significant improvements over conventional cepstral mean normalization (CMN) in a reverberant environment. In this paper, we propose a blind dereverberation method based on generalized spectral subtraction (GSS), which has been shown to be effective for noise reduction, instead of power SS. Furthermore, we extend the missing feature theory (MFT), which was initially proposed to enhance the robustness of additive noise, to dereverberation. A one-stage dereverberation and denoising method based on GSS is presented to simultaneously suppress both the additive noise and nonstationary multiplicative noise (reverberation). The proposed dereverberation method based on GSS with MFT is evaluated on a large vocabulary continuous speech recognition task. When the additive noise was absent, the dereverberation method based on GSS with MFT using only 2 microphones achieves a relative word error reduction rate of 11.4 and 32.6% compared to the dereverberation method based on power SS and the conventional CMN, respectively. For the reverberant and noisy speech, the dereverberation and denoising method based on GSS achieves a relative word error reduction rate of 12.8% compared to the conventional CMN with GSS-based additive noise reduction method. We also analyze the effective factors of the compensation parameter estimation for the dereverberation method based on SS, such as the number of channels (the number of microphones), the length of reverberation to be suppressed, and the length of the utterance used for parameter estimation. The experimental results showed that the SS-based method is robust in a variety of reverberant environments for both isolated and continuous speech recognition and under various parameter estimation conditions.

A Study on the Redundancy Reduction in Speech Recognition

The characteristic features of speech signal do not vary significantly from frame to frame. Therefore, it is advisable to reduce the redundancy involved in the similar feature vectors. The objective of this paper is to search for the optimal condition of minimum redundancy and maximum relevancy of the speech feature vectors in speech recognition. For this purpose, we realize redundancy reduction by way of a vigilance parameter and investigate the resultant effect on the speaker-independent speech recognition of isolated words by using FVQ/HMM. Experimental results showed that the number of feature vectors might be reduced by 30% without deteriorating the speech recognition accuracy.

A Noise-Robust Continuous Speech Recognition System Using Block-Based Dynamic Range Adjustment

A new approach to speech feature estimation under noise circumstances is proposed in this paper. It is used in noise-robust continuous speech recognition (CSR). As the noise robust techniques in isolated word speech recognition, the running spectrum analysis (RSA), the running spectrum filtering (RSF) and the dynamic range adjustment (DRA) methods have been developed. Among them, only RSA has been applied to a CSR system. This paper proposes an extended DRA for a noise-robust CSR system. In the stage of speech recognition, a continuous speech waveform is automatically assigned to a block defined by a short time length. The extended DRA is applied to these estimated blocks. The average recognition rate of the proposed method has been improved under several different noise conditions. As a result, the recognition rates are improved up to 15% in various noises with 10 dB SNR.

Real Time Isolated Word Speech Recognition System for Human Computer Interaction

paper introduces a new approach to develop a real time isolated word speech recognition system for human computer interaction. The system is a speaker dependent system. The main task is to recognize list of words in which the speaker says through the microphone. The features used are the mel-frequecy cepstarl coefficients (MFCC) which gives the good discrimination of the speech signal. The Dynamic Programming algorithm is used in the system measures the similarity between the stored template and the test template for the speech recognition which gives the optimum distance. The recognition accuracy obtained for the system is 88.0%. We made a simple list of ten words of cities names in India in which for displaying the images of the cities when the word is spoken which can be used in tourism application. This work can be used in many areas after a little modification for the specific function for example to control the robot using simple commands and also in many applications.

Integrated Phoneme Subspace Method for Speech Feature Extraction

Speech feature extraction has been a key focus in robust speech recognition research. In this work, we discuss data-driven linear feature transformations applied to feature vectors in the logarithmic mel-frequency filter bank domain. Transformations are based on principal component analysis (PCA), independent component analysis (ICA), and linear discriminant analysis (LDA). Furthermore, this paper introduces a new feature extraction technique that collects the correlation information among phoneme subspaces and reconstructs feature space for representing phonemic information efficiently. The proposed speech feature vector is generated by projecting an observed vector onto an integrated phoneme subspace (IPS) based on PCA or ICA. The performance of the new feature was evaluated for isolated word speech recognition. The proposed method provided higher recognition accuracy than conventional methods in clean and reverberant environments.

스마트 홈 환경에서 사용자 상황정보 기반의 음성 인식 시스템 개발

Most speech recognition systems that have a large capacity and high recognition rates are isolated word speech recognition systems. In order to extend the scope of recognition, it is necessary to increase the number of words that are to be searched. However, it shows a problem that exhibits a decrease in the system performance according to the increase in the number of words. This paper defines the context information that affects speech recognition in a ubiquitous environment to solve such a problem and develops user localization method using inertial sensor and RFID. Also, we develop a new speech recognition system that demonstrates better performances than the existing system by establishing a word model domain of a speech recognition system by context information. This system shows operation without decrease of recognition rate in smart home environment.