Malayalam Isolated Digit Recognition using HMM and PLP cepstral coefficient

Development of Malayalam speech recognition system is in its infancy stage; although many works have been done in other Indian languages. In this paper we present the first work on speaker independent Malayalam isolated speech recognizer based on PLP (Perceptual Linear Predictive) Cepstral Coefficient and Hidden Markov Model (HMM). The performance of the developed system has been evaluated with different number of states of HMM (Hidden Markov Model). The system is trained with 21 male and female speakers in the age group ranging from 19 to 41 years. The system obtained an accuracy of 99.5% with the unseen data

A Comparative study of HMM and SVM in Malayalam Digit Recognition

A primary medium for the human beings to communicate through language is Speech. Automatic Speech Recognition is wide spread today. Recognizing single digits is vital to a number of applications such as voice dialling of telephone numbers, automatic data entry, credit card entry, PIN (personal identification number) entry, entry of access codes for transactions, etc. In this paper we present a comparative study of SVM (Support Vector Machine) and HMM (Hidden Markov Model) to recognize and identify the digits used in Malayalam speech.

PSWT Based Linear Predictive Coding and Development of a Parallel Multiple Subsequence Structure for DWT Computation

During 1990's the Wavelet Transform emerged as an important signal processing tool with potential applications in time-frequency analysis and non-stationary signal processing.Wavelets have gained popularity in broad range of disciplines like signal/image compression, medical diagnostics, boundary value problems, geophysical signal processing, statistical signal processing,pattern recognition,underwater acoustics etc.In 1993, G. Evangelista introduced the Pitch- synchronous Wavelet Transform, which is particularly suited for pseudo-periodic signal processing.The work presented in this thesis mainly concentrates on two interrelated topics in signal processing,viz. the Wavelet Transform based signal compression and the computation of Discrete Wavelet Transform. A new compression scheme is described in which the Pitch-Synchronous Wavelet Transform technique is combined with the popular linear Predictive Coding method for pseudo-periodic signal processing. Subsequently,A novel Parallel Multiple Subsequence structure is presented for the efficient computation of Wavelet Transform. Case studies also presented to highlight the potential applications.

Design and fabrication of a photothermal spectrometer and investigations of multilayer thin films"

In this work we present the results of our attempt to build a compact photothermal spectrometer capable of both manual and automated mode of operation.The salient features of the system include the ability to analyse thin film, powder and polymer samples. The tool has been in use to investigate thermal, optical and transport properties. Binary and ternary semiconducting thin films were analysed for their thermal diffusivities. The system could perform thickness measurements nondestructively. Ion implanted semiconductors are widely studied for the effect of radiation induced defects. We could perform nondestructive imaging of defects using our spectrometer.The results reported in his thesis on the above in addition to studies on In2S3 and transparent conducting oxide ZnO have been achieved with this spectrometer. Various polymer samples have been easily analysed for their thermal diffusivities. The technique provided ease of analysis not achieved with conventional techniques like TGA and DSC. Industrial application of the tool has also been proved by analyzing defects of welded joints and adhesion of paints. Indigenization of the expensive lock-in-amplifier and automation has been the significant achievement in the course of this dissertation. We are on our way to prove the noise rejection capabilities of our PC LIA.

Realisation of a Target Classifier For Noise Sources in the Ocean

This thesis addresses one of the emerging topics in Sonar Signal Processing.,viz.the implementation of a target classifier for the noise sources in the ocean, as the operator assisted classification turns out to be tedious,laborious and time consuming.In the work reported in this thesis,various judiciously chosen components of the feature vector are used for realizing the newly proposed Hierarchical Target Trimming Model.The performance of the proposed classifier has been compared with the Euclidean distance and Fuzzy K-Nearest Neighbour Model classifiers and is found to have better success rates.The procedures for generating the Target Feature Record or the Feature vector from the spectral,cepstral and bispectral features have also been suggested.The Feature vector ,so generated from the noise data waveform is compared with the feature vectors available in the knowledge base and the most matching pattern is identified,for the purpose of target classification.In an attempt to improve the success rate of the Feature Vector based classifier,the proposed system has been augmented with the HMM based Classifier.Institutions where both the classifier decisions disagree,a contention resolving mechanism built around the DUET algorithm has been suggested.

Adrenergic and serotonergic function in dna synthesis during rat liver regeneration and in hepatocyte cultures

The adult mammalian liver is predominantly in a quiescent state with respect to cell division. This quiescent state changes dramatically, however, if the liver is injured by toxic, infectious or mechanic agents (Ponder, 1996). Partial hepatectomy (PH) which consists of surgical removal of two-thirds of the liver, has been used to stimulate hepatocyte proliferation (Higgins & Anderson 1931). This experimental model of liver regeneration has been the target of many studies to probe the mechanisms responsible for liver cell growth control (Michalopoulos, 1990; Taub, 1996). After PH most of the remaining cells in the renmant liver respond with co-ordinated waves of DNA synthesis and divide in a process called compensatory hyperplasia. Hence, liver regeneration is a model of relatively synchronous cell cycle progression in vivo. In contrast to hepatomas, cell division is terminated under some intrinsic control when the original cellular mass has been regained. This has made liver regeneration a useful model to dissect the biochemical and molecular mechanisms of cell division regulation. The liver is thus, one of the few adult organs that demonstrates a physiological growth rewonse (Fausto & Mead, 1989; Fausto & Webber, 1994). The regulation of liver cell proliferation involves circulating or intrahepatic factors that are involved in either the priming of hepatocytes to enter the cell cycle (Go to G1) or progression through the cell cycle. In order to understand the basis of liver regeneration it is mandatory to define the mechanisms which (a) trigger division, (b) allow the liver to concurrently grow and maintain dilferentiated fimction and (c) terminate cell proliferation once the liver has reached the appropriate mass. Studies on these aspects of liver regeneration will provide basic insight of cell growth and dilferentiation, liver diseases like viral hepatitis, toxic damage and liver transplant where regeneration of the liver is essential. In the present study, Go/G1/S transition of hepatocytes re-entering the cell cycle after PH was studied with special emphasis on the involvement of neurotransmitters, their receptors and second messenger function in the control of cell division during liver regeneration

Development Of A Pos Tagger For Malayalam-An Experience

A Parts of Speech tagger for Malayalam which uses a stochastic approach has been proposed. The tagger makes use of word frequencies and bigram statistics from a corpus. The morphological analyzer is used to generate a tagged corpus due to the unavailability of an annotated corpus in Malayalam. Although the experiments have been performed on a very small corpus, the results have shown that the statistical approach works well with a highly agglutinative language like Malayalam

Speech Recognition of Malayalam Numbers

Digit speech recognition is important in many applications such as automatic data entry, PIN entry, voice dialing telephone, automated banking system, etc. This paper presents speaker independent speech recognition system for Malayalam digits. The system employs Mel frequency cepstrum coefficient (MFCC) as feature for signal processing and Hidden Markov model (HMM) for recognition. The system is trained with 21 male and female voices in the age group of 20 to 40 years and there was 98.5% word recognition accuracy (94.8% sentence recognition accuracy) on a test set of continuous digit recognition task.

Automated Transcription System for Malayalam Language

Malayalam is one of the 22 scheduled languages in India with more than 130 million speakers. This paper presents a report on the development of a speaker independent, continuous transcription system for Malayalam. The system employs Hidden Markov Model (HMM) for acoustic modeling and Mel Frequency Cepstral Coefficient (MFCC) for feature extraction. It is trained with 21 male and female speakers in the age group ranging from 20 to 40 years. The system obtained a word recognition accuracy of 87.4% and a sentence recognition accuracy of 84%, when tested with a set of continuous speech data.

Development & evaluation of different acoustic models for Malayalam continuous speech recognition

Performance of any continuous speech recognition system is dependent on the accuracy of its acoustic model. Hence, preparation of a robust and accurate acoustic model lead to satisfactory recognition performance for a speech recognizer. In acoustic modeling of phonetic unit, context information is of prime importance as the phonemes are found to vary according to the place of occurrence in a word. In this paper we compare and evaluate the effect of context dependent tied (CD tied) models, context dependent (CD) and context independent (CI) models in the perspective of continuous speech recognition of Malayalam language. The database for the speech recognition system has utterance from 21 speakers including 11 female and 10 males. Our evaluation results show that CD tied models outperforms CI models over 21%.

Connected digit speech recognition system for Malayalam language

A connected digit speech recognition is important in many applications such as automated banking system, catalogue-dialing, automatic data entry, automated banking system, etc. This paper presents an optimum speaker-independent connected digit recognizer forMalayalam language. The system employs Perceptual Linear Predictive (PLP) cepstral coefficient for speech parameterization and continuous density Hidden Markov Model (HMM) in the recognition process. Viterbi algorithm is used for decoding. The training data base has the utterance of 21 speakers from the age group of 20 to 40 years and the sound is recorded in the normal office environment where each speaker is asked to read 20 set of continuous digits. The system obtained an accuracy of 99.5 % with the unseen data.