Teaching Documents by Joyprakash Lairenlakpam
Circuit analysis in the frequency domain [phasor analysis, to be specific] for sinusoidal sources... more Circuit analysis in the frequency domain [phasor analysis, to be specific] for sinusoidal sources: single source [cosine and sine functions] circuits, and circuits having double sources with the same frequency or the different frequencies
Electrical Circuit Analysis using Laplace Transform: Circuits with DC Sources and Passive Circuit... more Electrical Circuit Analysis using Laplace Transform: Circuits with DC Sources and Passive Circuit Elements (RLC)
Different techniques for nodal analysis while 1. choosing a reference node, 2. applying KCL at a... more Different techniques for nodal analysis while 1. choosing a reference node, 2. applying KCL at a node, and 3. using graph theory with KCL
Electrical Network Topology, Electrical Network Graph Theory, Tie-set, fundamental-circuit(f-circ... more Electrical Network Topology, Electrical Network Graph Theory, Tie-set, fundamental-circuit(f-circuit)/-loop(f-loop), Tie-set matrix
Electrical Network Topology, Electrical Network Graph Theory, Incidence Matrices of Electrical Ne... more Electrical Network Topology, Electrical Network Graph Theory, Incidence Matrices of Electrical Network [Complete incidence and reduced incidence matrices]
Electrical Network Topology, Electrical Network Graph Theory, Node, Branch, Twig, Link, Tree, Cotree
Circuit analysis in the frequency domain [phasor analysis, to be specific] for sinusoidal sources... more Circuit analysis in the frequency domain [phasor analysis, to be specific] for sinusoidal sources: single source [cosine and sine functions] circuits, and circuits having double sources with the same frequency or the different frequencies
Review of Basics of Electrical Networks: Circuit element, Node, Branch, Path, Network, Circuit, M... more Review of Basics of Electrical Networks: Circuit element, Node, Branch, Path, Network, Circuit, Mesh, Loop, Planar Circuit
Midterm question and answer for the paper - EE - 304 Electrical Network Theory
Problems related to graph theory [Q1, Q2, Q9] have been left out as they can be solved in various... more Problems related to graph theory [Q1, Q2, Q9] have been left out as they can be solved in various ways ...
Electrical Network Theory, Class Test
Electrical Network Theory
Electrical Network Theory mid semester question
Electrical Network Topology, Electrical Network Graph Theory, Cut-set matrix
Electrical Network Topology/Electrical Network Graph Theory: Complete Incidence Matrix, Reduced o... more Electrical Network Topology/Electrical Network Graph Theory: Complete Incidence Matrix, Reduced or Incidence Matrices of Electrical Network, Possible trees that can be drawn out of a given graph
Papers by Joyprakash Lairenlakpam
Development of language identification system using MFCC and vector quantization
2017 IEEE 4th International Conference on Smart Instrumentation, Measurement and Application (ICSIMA), 2017
ABSTRACT This paper describes the studies towards the development of a Language Identification (L... more ABSTRACT This paper describes the studies towards the development of a Language Identification (LID) System for Manipuri, Assamese and Bengali Language using Phonetic Engine (PE). A PE is a system used to capture the phonetic information of the speech signal and to transform that into symbolic form. Around 5 hours read speech data have been collected for each of these languages for training and testing purposes. The collected speech data of Manipuri, Assamese and Bengali languages consist of 16, 31 and 43 speakers respectively. We used a 5-state left to right Hidden Markov Model (HMM) with 32 Gaussian mixtures per state to build an acoustic model for each phonetic unit of Manipuri, Assamese and Bengali languages. The Manipuri, Assamese and Bengali PEs were run over test utterances belonging to any of these languages. The PE which gives the maximum likelihood score corresponds to the identified language.
Development of Manipuri Phonetic Engine
Signal to symbol conversion plays a vital role in speech processing. The Phonetic Engine can be e... more Signal to symbol conversion plays a vital role in speech processing. The Phonetic Engine can be employed for this conversion. It can also extract the acoustic information of the speech signal to improve the performance of existing phone recognizers. This paper describes the studies about the development of Manipuri Phonetic Engine. The speech data in Manipuri language are collected in three different modes, viz. reading, lecture and conversation. However, only the read mode data has been used to build up the database for training and testing the system. Around 5 hours of read speech are collected from 6 female and 4 male speakers. The symbols of International Phonetic Alphabet (IPA) are used during transcription the read speech data. A 5- state left to right Hidden Markov Model (HMM) with a 32 mixture continuous density diagonal covariance Gaussian mixture model (GMM) per state is used to build a model for each phonetic unit. The HMM tool kit (HTK), version 3.4 is used in building u...
A Simple Theoretical Analysis of the Thermo Electric Power in Strained Layer Quantum Dot Superlattices with Graded Interfaces in the Presence of a Large Magnetic Field
With the advent of MBE, FLL, MOCVD and other modern experimental techniques, the semiconductor su... more With the advent of MBE, FLL, MOCVD and other modern experimental techniques, the semiconductor superlattices (SLs) as originally proposed by Esaki and Tsu have found wide applications in many new device structures. Most papers in this area are based on the assumption that the interface between the layers is sharply defined with the zero thickness. The advanced methods may produce SL with physical interface between the two materials crystallographically abrupt, but the bonding environment of the atoms adjoining these interface will change at least on an atomic scale as the potential form changes from a well (barrier) to a barrier (well), an intermediate potential region exists for the charge carriers. Thus, the influence of the finite thickness of the interface on the carrier dispersion law becomes very important since the dispersion relation of the carriers governs all the transport properties. In this paper, we shall study the thermo electric power in the presence of large magnetic...
Design of Manipuri Keywords Spotting System using HMM
2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), 2013
ABSTRACT This paper aims to discuss the implementation of phoneme based Manipuri Keyword Spotting... more ABSTRACT This paper aims to discuss the implementation of phoneme based Manipuri Keyword Spotting System (MKWSS). Manipuri is a scheduled Indian language of Tibeto-Burman origin. Around 5 hours of read speech are collected from 4 male and 6 female speakers for development of database of MKWSS. The symbols of International Phonetic Alphabet (IPA)(revised in 2005) are used during the transcription of the data. A five state left to right Hidden Markov Model (HMM) with 32 mixture continuous density diagonal covariance Gaussian Mixture Model (GMM) per state is used to build a model for each phonetic unit. We have used HMM tool kit (HTK), version 3.4 for modeling the system. The system can recognize 29 phonemes and a non-speech event (silence) and will detect the present keywords formed by these phonemes. Continuous Speech data have been collected from 5 males and 8 females for analysing the performance of the system. The performance of the system depends on the ability of detection of the keywords. An overall performance of 65.24% is obtained from the phoneme based MKWSS.
Development of Manipuri Phonetic Engine and its application in language identification
ABSTRACT
Uploads
Teaching Documents by Joyprakash Lairenlakpam
Papers by Joyprakash Lairenlakpam