A MICROCOMPUTER BASED SPEECH RECOGNITION SYSTEM Edward

نویسنده

  • Ching Y. Suen
چکیده

41 This paper describes the properties of speech and a system which recognizes speech by means of a microcomputer system. It is implemented on an 8-bit microcomputer which uses a 280 central processing unit and an analog to digital interface for the acquisition and preprocessing of the speech signal obtained from a microphone. The system is designed to adapt itself to recognize words from different speakers by changing the stored acoustic parameters. Experiments on a large number of samples show that after careful training, recognition of isolated words is attained with a high degree of accuracy. UN SYST~ME POUR LA RECONNAISSANCE DE LA PAROLE, BAS~ SUR UN MICROPROCESSEUR La presente communication decrit les proprietes de la parole et un systeme de reconnaissance de la parole utilisant un micro-ordinateur. Ce systeme est mis en oeuvre dans un micro-ordinateur a 8 bits dont l'unite centrale est une pastille 280, et qui comprend un interface analogique-numerique pour la saisie et le pre-traitement du signal audio capte par un microphone. 11 a ete con~u pour s'adapter de luimeme a la reconnaissance des mots prononces par diverses personnes, en modifiant les parametres acoustiques mis en memoire. Des experiences portant sur un grand nombre d'echantillons montrent, quIa la suite d'un apprentissage minutieux, ce systeme peut reconnaitre avec un degre eleve de precision des mots detaches.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Persian Phone Recognition Using Acoustic Landmarks and Neural Network-based variability compensation methods

Speech recognition is a subfield of artificial intelligence that develops technologies to convert speech utterance into transcription. So far, various methods such as hidden Markov models and artificial neural networks have been used to develop speech recognition systems. In most of these systems, the speech signal frames are processed uniformly, while the information is not evenly distributed ...

متن کامل

A Microcomputer-Based Simulator for Digital Control Systems

A microcomputer-based simulator for digital control systems is proposed. The proposed simulator is a hybrid system in which the plant is simulated by conventional method of analog computers and other parts of the system including generation of input signal is performed digitally, using a Z-80 based microcomputer. To overcome the difficulty of programming in assembly language, and at the same ti...

متن کامل

Speech Emotion Recognition Based on Power Normalized Cepstral Coefficients in Noisy Conditions

Automatic recognition of speech emotional states in noisy conditions has become an important research topic in the emotional speech recognition area, in recent years. This paper considers the recognition of emotional states via speech in real environments. For this task, we employ the power normalized cepstral coefficients (PNCC) in a speech emotion recognition system. We investigate its perfor...

متن کامل

A Signal Processing System based upon Monolithic Neural Coprocessors

A signal processing system based upon a custommade neural coprocessor integrated circuit is presented. The system comprises a dedicated PCB containing up to four coprocessors, which works in association with a microcomputer. All control and communication software, including a program for neural network training, were also developed. A speech recognition application and a performance evaluation ...

متن کامل

Speaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation

A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015