Conference Papers (Centre for Research on Bangla Language Processing)

Browse

Author: search.filters.author.Habib, S. M. MurtozaHas files: Yes

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    Acoustic analysis of Bangla consonants
    (BRAC University, 2008) Alam, Firoj; Habib, S. M. Murtoza; Khan, Mumit
    This paper describes the acoustic characteristics of Bangla consonants, obtained by analyzing the recordings of male and female voices. First, the duration of each phoneme was identified by averaging both the male and female voice data; then, formant were measured and formant comparison was made for controversial phonemes, which also served to resolve the controversies in the existing phoneme inventories; and finally, a consonant phoneme inventory was designed.
  • Thumbnail Image
    Item
    Segmentation free Bangla OCR using HMM: Training and recognition
    (BRAC University, 2007) Hasnat, Md. Abul; Habib, S. M. Murtoza; Khan, Mumit
    The wide area of the application of HMM is in Speech Recognition where each spoken word is considered as a single unit to be recognized from the trained word network. Using this concept some research has been done for character recognition. In this paper, we present the training and recognition mechanism of a Hidden Markov Model (HMM) based multi font supported Optical Character Recognition (OCR) system for Bangla character. In our approach the central idea is separate HMM model for each segmented character or word. We emphasize on word level segmentation and like to consider the single character as a word when the character appears alone after segmentation process is done. The system uses HTK toolkit for data preparation, model training from multiple samples and recognition. Features of each trained character are calculated by applying Discrete Cosine Transform (DCT) to each pixel value of the character image where the image is divided into several frames according to its size. The extracted features of each frame are used as discrete probability distributions that will be given as input parameter to each HMM model. In case of recognition a model for each separated character or word is build up using the same approach. This model is given to the HTK toolkit to perform the recognition using Viterbi Decoding. The experimental result shows significant performance.
  • Thumbnail Image
    Item
    Development of annotated Bangla speech corpora
    (BRAC University, 2010) Alam, Firoj; Habib, S. M. Murtoza; Sultana, Dil Afroza; Khan, Mumit
    This paper describes the development procedure of three different Bangla read speech corpora which can be used for phonetic research and developing speech applications. Several criteria were maintained in the corpora development process that includes considering the phonetic and prosodic features during text selection. On the other hand, a specification was maintained in the recording phase as the speaking style is a vital part in speech applications. We also concentrated on proper text normalization, pronunciation, aligning, and labeling. The labeling was done manually – in the present endeavor sentence level labeling (annotation) was completed by maintaining a specification so that it could be expanded in future.
  • Thumbnail Image
    Item
    A high performance domain specific OCR for Bangla script
    (BRAC University, 2007) Hasnat, Md. Abul; Habib, S. M. Murtoza; Khan, Mumit
    Research on recognizing Bengali script has been started since mid 1980’s. A variety of different techniques have been applied and the performance is examined. In this paper we present a high performance domain specific OCR for recognizing Bengali script. We select the training data set from the script of the specified domain. We choose Hidden Markov Model (HMM) for character classification due to its simple and straightforward way of representation. We examine the primary error types that mainly occurred at preprocessing level and carefully handled those errors by adding special error correcting module as a part of recognizer. Finally we added a dictionary and some error specific rules to correct the probable errors after the word formation is done. The entire technique significantly increases the performance of the OCR for a specific domain to a great extent.
  • Thumbnail Image
    Item
    Skew angle detection of bangla script using radon transform
    (BRAC University, 2006) Habib, S. M. Murtoza; Noor, Nawsher Ahamed; Khan, Mumit
    Skew angle detection and correction an integral part of any OCR system. Without proper skew correction, the performance of an OCR will simply not be acceptable for most scanned images. We propose an innovative method for skew angle detection and correction for Bangla scripts using the Radon Transform. The basic idea is to identify the upper envelope by detecting the headline that accompanies most of the letters in the Bangla script, and then apply the Radon Transform to this upper envelope to get the skew angle. Once the angle is known, the correction is quite trivial to perform. While the current implementation handles only a single skew angle per text image, it can be extended to handle multiple skew angles by partitioning the document image.