Theses and Dissertations

Permanent URI for this collectionhttp://ir.daiict.ac.in/handle/123456789/1

Browse

Subject: search.filters.subject.Signal Processing

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    The Study of Cycles in 2-connected Graphs Specifically Odd Graphs
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2018) Thakker, Avani; Muthu, Rahul
    Counting the number of cycles in an undirected graph is a classical problemwhich is known to be intractable and so research on this problem typically focuses on approximation algorithms, special cases, heuristics and some variants of the problem. This problem has been extensively studied for its applications in areas of communication systems, artificial intelligence and signal processing. In Complexity theory, this problem lies in the class of #P-complete problem. There may be exponentially many simple cycles in a graph. We observed growth in the number of cycles by adding ears to a 2-connected graph. As analyzed, the growth was exponential. Counting or finding cycles and paths of graphs like complete graphs, presents no interest, in particular since everything is already known analytically. Hence, we studied the cycle structure in Odd Graphs. We analytically obtained cycle lengths that are certainly present in an odd graph without traversing the graph structure. Further, we added minimal number of edges to an odd graph to make the graph pancyclic.
  • Thumbnail Image
    ItemOpen Access
    Post-processing of speech signal for prosody modification and improvement
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2014) Dhoot, Kuldeep; Patil, Hemant A.
    The basic task of a text-to-speech (TTS) synthesis system is to obtain the correct synthetic speech signal with the help of machines corresponding to the given input text. However, the main difficulty with the TTS system is the problem of appropriate prosody in the resultant speech signal. In this thesis, we used the methods based on the pitch synchronous overlap-add (PSOLA) technique, i.e., time-domain PSOLA (TD-PSOLA) and linear prediction PSOLA (LP-PSOLA), which tries to use the combination of different pitch-scale and time-scale combination to match the synthesized speech to the natural speech. To implement the PSOLA techniques, different pitch detection algorithms are employed in order to obtain the pitch marks and pitch contour. Pitch marking is essential task to obtain the required time-scale and pitch-scale modifications. Pitch detection algorithms based on autocorrelation function (ACF), normalized cross-correlation function (NCCF) and zero frequency resonator (ZER) are employed in this thesis. Firstly, we applied the PSOLA methods to the unit selection synthesis (USS) and Hidden Markov model-based TTS (HTS) based synthesized speech for which we were having the prior knowledge of natural speech corresponding to the synthesized speech. Later, we performed the method on the Blizzard Challenge-2012 speech corpus for which we were not having the database of corresponding natural signal. PSOLA method is also applied only on the natural speech for time-scale and pitch-scale modifications. Time-scale modification of natural speech have many real world applications speech, a series of tests are then performed to determine the effectiveness of the PSOLA methods.
  • Thumbnail Image
    ItemOpen Access
    HMM-based speech synthesis system (HTS) for Gujarati language.
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2013) Shah, Nirmesh Jayeshkumar; Patil, Hemant A.
    Hidden Markov Models (HMM) have been applied successfully to Automatic Speech Recognition (ASR) problems and are currently applied in speech synthesis applications. In this thesis, HMM-based Speech Synthesis System (HTS) for TTS is understood in detail and applied to Gujarati language. In particular, for HTS implementation, issues related to characteristics of Gujarati language are identified and their solutions are also discussed in this work. Furthermore, classification of Gujarati characters have also been done for preparation of question set. We have done comparison of conventional Baum-Welch algorithm which is the ExpectationMaximization (EM) algorithm for discrete finite state HMMs and DeterministicAnnealingExpectation Maximization (DAEM) algorithm in the context of HTS as applied to Gujarati language. Detail study on derivation of EM and DAEM algorithms alongwith examples have also been presented. Based on the subjective evaluations of HTS system, it was observed that HTS voices developed for Gujarati language has very high intelligibility. We found that as amount of training data increases, MOS of HTS voice improves. From results, we found that for 70.5 % of time people have preferred DAEM-based HTS than EM-based HTS. We also found that runtime memory of HTS developed for Gujarati language is in the order of few megabytes. Hence, it can be very useful for applications which suffer from memory limitations, such as mobiles and tablets.