Isolated Word Speech Recognition System Research Articles

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%.

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.

A Recognition Judgment Method of Isolated-Word Speech-Recognition

Isolated-word speech-recognition system adopted the shortest distance of Dynamic Time Warping (DTW) to make recognition judgment, which has the disadvantage of high False Accept Rate (FAR), poor anti-noise and robustness. This paper proposes a new method based on DTW distance Threshold Estimation for recognition judgment. This method processes the maximum distance between template speech and training input speech multiplying adjusting coefficient, then plus noise DTW distance, which regard the final result as distance Threshold Estimation. At the time of doing speech recognition, if the distance between testing speech and template speech exceeds the Threshold Estimation, then the system will not recognize this speech. The experiment shows that this method can greatly improve the anti-noise and robustness performance of the Isolated-word speech-recognition system and solve the problem of high FAR.

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.

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.

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.

Robust speech parameter based on a psychoacoustical rule-base model

To realize a speech recognition system for our daily life, surrounding noise needs to be considered. Many studies have been done for parameters which are robust in a noisy environment. This paper presents a new parameter which is based on a psychoacoustical rule-base model. First the spectral local peaks of formants are calculated as a basic parameter. By performing this operation frame by frame, the parameter can be represented in a three-dimensional form like a spectrogram. The parameter is then modified by applying psychoacoustical rules to the sequence of peaks, corresponding to a so-called ‘‘auditory stream’’ in a speech. The parameter modification utilizes the characteristics of the parameter such as the synchronous onset or offset, the continuity of sequential peaks, and so on. The efficiency of the proposed parameter is evaluated on an isolated word speech recognition system with various SNR. As a result, the improvement due to the proposed parameter is at least 4 dB in SNR for white noise, in comparison with the performance of a LPC-based system.

Training module for estimating mixture Gaussian densities for speech-unit models in speech recognition systems

A model-training module generates mixture Gaussian density models from speech training data for continuous, or isolated word speech recognition systems. Speech feature sequences are labeled into segments of states of speech units using Viterbi-decoding based optimized segmentation algorithm. Each segment is modeled by a Gaussian density, and the parameters are estimated by sample mean and sample covariance. A mixture Gaussian density is generated for each state of each speech unit by merging the Gaussian densities of all the segments with the same corresponding label. The resulting number of mixture components is proportional to the dispersion and sample size of the training data. A single, fully merged, Gaussian density is also generated for each state of each speech unit. The covariance matrices of the mixture components are selectively smoothed by a measure of relative sharpness of the Gaussian density and the smoothing can also be done blockwise. The weights of the mixture components are set uniformly initially, and are reestimated using a segmental-average procedure. The weighting coefficients, together with the Gaussian densities, then become the models of speech units for use in speech recognition.

A robust speaker-independent isolated word HMM recognizer for operation over the telephone network

This paper presents the results of a speaker-independent, isolated word speech recognition system developed for information access over Australian public switched telephone network (PSTN). The recognition system is based on Continuous Density Hidden Markov Modelling (CDHMM). The speech database was collected over the PSTN from a large variety of speakers and different geographical locations. The database contained a vocabulary of 55 words consisting of 41 country names and their variations plus a few control words. The recognition performance, tested on 100 other speakers (50 males and 50 females) with no grammar constraint, resulted in an overall recognition rate of 97.3%. This paper describes the HMM training methodology, which consisted of three stages: hand segmented seed model training, automatic word segmentation and reestimation. To facilitate the future implementation of the recognition system in a DSP environment, a fast frame synchronous Viterbi algorithm was implemented with no degradation in recognition performance. The end-point detection is performed by the combination of the silence/noise model with the word models. For confusable word pairs, sub-word models are used to improve the recognition rate. A post-processing approach is used to enhance the performance of the recognition system, in which all ranked candidates from the Viterbi decoding are subject to the tests of the minimum word duration and the likelihood difference between the first candidate and the second candidate.

An FFT-based speech recognition system

A speaker-dependent, isolated-word speech recognition system is presented which is based on the use of the fast Fourier transform for extracting features from the speech input. The algorithm then normalizes those features and compares them against previously stored word templates using dynamic time warping in order to identify the uttered word. The system has been successfully implemented and provided good results when tested using a small dictionary.

Evaluation of the smoothed group delay spectrum distance measure for speaker‐dependent speech recognition

AbstractThis paper evaluates first the smoothed group delay spectrum (SGDS) distance measure through the isolated work speech recognition experiment by specified speakers. The experiment was performed for the following three cases, considering the speech recognition in the actual environment: 1) the case where the channels have difference characteristics; 2) the case where a white noise is added to the input speech; and 3) the case where the telephone speech is used as the input.In all three cases, the recognition rate is improved drastically compared to the traditional LPC cepstrum distance measure. An improvement of the recognition rate by 16 percent was realized under the noise of segmental SN ratio 20 dB. Then the distance measure is evaluated for the case where the FFT cepstrum is converted into the group delay spectrum.The proposed method gives a better recognition rate compared to the conventional FFT cepstrum distance measure, but the result is worse than the SGDA measure by approximately 3 percent since the higher‐order FFT cepstrum coefficient has a larger variance on the time axis.Finally, the SGDS distance measure is evaluated by the isolated word speech recognition system with the monosyllable as the registered speech. The vowel recognition rate is improved, which improved the recognition rates for the syllable and the word by 2 percent or more on a relative scale.

A PC-based very large vocabulary isolated word speech recognition system

The Speech Recognition Group at Olivetti has designed an isolated word recognition system for Italian which can accept a very large vocabulary in excess of 60,000 words and recognize words in real time. The system fits into a 386-based personal computer and runs under MS-DOS. Among its most appealing features are the very quick and application-independent procedure for training the system to the user's voice and the easy way in which application dictionaries can be created. What makes short training possible is the fact that the system extracts target spectral distributions of phonemes from the training words and combines this speaker-dependent information with speaker-independent information concerning other aspects of the speech signal such as energy profile, phoneme durations, and phoneme similarity. The system accepts natural language without any restriction and can be used to dictate documents of any kind, provided the dictionary of the application domain is specified. Dictation, however, is not the only application we envisage. In this paper we describe our approach to speech recognition and provide some information on the actual implementation and performance of our system.

Noise adaptation in a hidden Markov model speech recognition system

Several ways for making the signal processing in an isolated word speech recognition system more robust against large variations in the background noise level are presented. Isolated word recognition systems are sensitive to accurate silence detection, and are easily overtrained on the specific noise circumstances of the training environment. Spectral subtraction provides good noise immunity in the cases where the noise level is lower or slightly higher in the testing environment than during training. Differences in residual noise energy after spectral subtraction between a clean training and noisy testing environment can still cause severe problems. The usability of spectral subtraction is largely increased if complemented with some extra noise immunity processing. This is achieved by the addition of artificial noise after spectral subtraction or by adaptively re-estimating the noise statistics during a training session. Both techniques are almost equally successful in dealing with the noise. Noise addition achieves the additional robustness that the system will never be allowed to learn about low amplitude events that might not be observable in all environments; this is achieved, however, at a cost that some information is consistently thrown away in the most favorable noise situations.

Performance benchmarks for isolated word recognition

The performance of isolated word speech recognition systems has steadily improved over time as more is learned about how to represent the significant events in speech and how to capture these events via training algorithms. In particular, algorithms based on both template matching and hidden Markov models (HMMs) have been developed that yield high accuracy on several standard vocabularies including the ten digits (zero to nine) and the set of letters of the English alphabet. Results are presented here that show the effect of analysis parameters (e.g., frame size, frame rate) on recognition performance for a speaker trained system and the performance of both template and HMM-based recognizers (both speaker trained and speaker independent) on the digits and the alphabet vocabularies.

Some performance benchmarks for isolated work speech recognition systems

The performance of isolated word speech recognition system has steadily improved over time as we learn more about how to represent the significant events in speech, and how to capture these events via appropriate analysis procedures and training algorithms. In particular, algorithms based on both template matching (via dynamic time warping (DTW) procedures) and hidden Markov models (HMMs) have been developed which yield high accuracy on several standard vocabularies, including the 10 digits (zero to nine) and the set of 26 letters of the English alphabet (A-Z). Results are given showing currently attainable performance of a laboratory system for both template-based (DTW) and HMM-based recognizers, operating in both speaker trained and speaker independent modes, on the digits and the alphabet vocabularies using telephone recordings. We show that the average error rates of these systems, on standard vocabularies, are significantly lower than those reported several years back on the exact same databases, thereby reflecting the progress which has been made in all aspects of the speech recognition process.

Reference template adaptation in speaker-independent isolated word speech recognition

A technique which permits the adaptation of reference patterns (templates) in isolated word speech recognition systems is described. Experimental results for supervised and unsupervised adaptation with speaker-independent initial templates are presented.

A study of ambient and amplitude correction in isolated utterance recognition

Experiments demonstrating the importance of ambient and amplitude correction in an isolated word speech recognition system are reported. Whenever a speaker produces the speech input in a nonanechoic environment, such as in in ordinary office, the method of ambient correction helps to neutralize the effect of any change in ambient which would otherwise adversely influence the performance of the recognizer. On the other hand, the goal of amplitude correction is to compensate for amplitude level fluctuations encountered in any normal speech input. The experiments compare the performances with and without the corrections in the context of an experimental speech recognition system developed at IBM. A database consisting of the speech collected from three male and one female speaker is used for this study. Performance is measured by examining both the error rate and the time taken by the decoder. Significant improvement in performance is observed on both counts when the corrections are applied.