Implementation of Bangla Speech Recognition System on Cell Phones

نویسنده

  • Mumit Khan
چکیده

Implementation of Bangla Speech Recognition System on Cell Phones Speech Recognition refers to the process of converting analogue speech signals into text. Since the 1970s a lot of work has undergone in this particular field. The complex nature of speech due to it's contextual meaning , dialects, accents as well as the environment makes the task of recognizing speech very difficult. A lot of research is currently under progress to increase the accuracy of this system. Although extensive research has been done on other language, the field of automated speech recognition in Bangla is at it's early level. With almost 200 million Bangla speakers all over the world, there can be a lot of applications of speech recognition. Cellular phone is one such domain , where voice commands can be used to initiate tasks. High accuracy can be achieved as the number of commands are rather limited and since it is dependent upon the user's voice, extensive training will yield better results. If an application is developed for cellular phones that can execute Bangla voice commands, it will make it easier for a large number of disabled people to use cell phones in their own languages. Since a lot of the users are not literate about how to use commands by pressing keys of phones will be facilitated by this application. However, the limited processing power of the cell phones are also a challenging factor. The aim of this thesis was to show a way to develop an application that will be able to recognize Bangla voice commands for cell phone and execute them followed by an attempt to implement the system according to research findings and analyze it.

برای دانلود رایگان 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

Implementation Of Back-Propagation Neural Network For Isolated Bangla Speech Recognition

This paper is concerned with the development of Back-propagation Neural Network for Bangla Speech Recognition. In this paper, ten bangla digits were recorded from ten speakers and have been recognized. The features of these speech digits were extracted by the method of Mel Frequency Cepstral Coefficient (MFCC) analysis. The mfcc features of five speakers were used to train the network with Back...

متن کامل

Separating Words from Continuous Bangla Speech T

In this paper we present a new word separation algorithm for Real Time Speech i.e., Continuous Bangla Speech Recognition (CBSR). Prosody has great impact on Bangla speech and the algorithm is developed by considering prosodic feature with energy. Task of this algorithm is to separate Bangla speech into words. At first continuous Bangla speech are fed into the system and the word separation algo...

متن کامل

Performance Evaluation of Bangla Word Recognition Using Different Acoustic Features

This paper describes a medium size Bangla speech corpus preparation and the comparison of the performances of different acoustic features for Bangla word recognition. A small number of speakers are use for most of the Bangla automatic speech recognition (ASR) system, but 40 speakers selected from a wide area of Bangladesh, where Bangla is used as a native language, are involved here. In the exp...

متن کامل

Text Normalization System for Bangla

This paper describes a process of text normalization system for the Bangla language (exonym: Bengali) by identifying the semiotic classes from Bangla text corpus. After identifying the semiotic classes, a set of rules was written for tokenization and verbalization. This study is important for Text-ToSpeech (TTS) system and as well as for creating a language model used in speech recognition.

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2011