M Tech Dissertations

Permanent URI for this collectionhttp://drsr.daiict.ac.in/handle/123456789/3

Browse

Filters

20112

Settings

Subject: search.filters.subject.Hidden Markov Model

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Shallow parsing of Gujarati text
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2011) Dave, Vidhi; Pandya, Abhinay
    Shallow parsing is the process of assigning tag to minimal, non recursive phrase of the sentence. It is useful for many applications like question answering system, information retrieval where there is no need of full parsing. Gujarati is one of the main languages of India and 26th most spoken native language in the world. There are more than 50 million speakers of Gujarati language worldwide. Natural language processing of Gujarati is in its infancy. Now days there are many data available in Gujarati on websites but due to lack of resources it is hard for users to retrieve it efficiently. So, shallow parsing of Gujarati can make task easier for another tasks like machine translation, information extraction and retrieval. In this thesis, we have worked on the automatic annotation of Shallow Parsing of Gujarati. 400 sentences have been manually tagged. Different Machine Learning techniques namely Hidden Markov Model and Conditional Random Field have been used. We achieved good accuracy and it is similar to Hindi chunker even though resources available for Gujarati are very less. The best performance is achieved using CRF with contextual information and Part-of-speech tags.
  • Thumbnail Image
    ItemOpen Access
    Person recognition from their hum
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2011) Madhavi, Maulik C.; Patil, Hemant A.
    In this thesis, design of person recognition system based on person's hum is presented. As hum is nasalized sound and LP (Linear Predication) model does not characterize nasal sounds sufficiently, our approach in this work is based on using Mel filterbank-based cepstral features for person recognition task. The first task was consisted of data collection and corpus design procedure for humming. For this purpose, humming for old Hindi songs from around 170 subjects are used. Then feature extraction schemes were developed. Mel filterbank follows the human perception for hearing, so MFCC was used as state-of- the-art feature set. Then some modifications in filterbank structure were done in order to compute Gaussian Mel scalebased MFCC (GMFCC) and Inverse Mel scale-based MFCC (IMFCC) feature sets. In this thesis mainly two features are explored. First feature set captures the phase information via MFCC utilizing VTEO (Variable length Teager Energy Operator) in time-domain, i.e., MFCC-VTMP and second captures the vocal-source information called as Variable length Teager Energy Operator based MFCC, i.e., VTMFCC. The proposed feature set MFCCVTMP has two characteristics, viz., it captures phase information and other it uses the property of VTEO. VTEO is extension of TEO and it is a nonlinear energy tracking operator. Feature sets like VTMFCC captures the vocal-source information. This information exhibits the excitation mechanism in the speech (hum) production process. It is found to be having complementary nature of information than the vocal tract information. So the score-level fusion based approach of different source and system features improves the person recognition performance.