Home
About
Research
Blog
Resources
Contact
Resources
Deep Learning
Deep Neural Networks
Introduction, Architectures and Implementations
Reinforcement Learning
An introduction to the mathematics of artificial intelligence.
Biomechanical Modeling
A Subject-Adaptable Tongue Model in ArtiSynth
Available upon request!
Dynamics of a Single Joint Arm
A derivation of the dynamics of a single joint arm model.
HMMs for Speech Synthesis
Multi-Space Probability Distribution HMM
a new kind of HMM in which the state output probabilities are defined by multi-space probability distributions
Speech Parameter Generation Algorithms for HMM
Given HMM models an algorithm to generate smooth speech parameter trajectories is described.
Speech Parameter Generation Algorithms for HMM with Mixture Gaussian Distribution
Given Multi-mixture HMM models an algorithm to generate smooth speech parameter trajectories is described.
Adaptation Techniques for Hidden Markov Models
Describes popular speaker adaptation schemes that can be applied to continuous density hidden Markov models.
Language Processing
Document Clustering Techniques
An overview of different clustering techniques
HMM Based POS Tagger
HMMs applied to part of speech tagging.
Identifying Implicit Relationships
A description of how IBM Watson answers natural-language questions by identifying hidden associations and implicit relationships
Question Analysis: How Watson Reads A Clue?
A description of the techniques used by Watson to understand what the question is asking for?
Text to Speech Synthesis
A description of the processes involved in conversion of arbitrary text to speech waveform.
Music Notation Software
Introduction to MusicXML
MusicXML is a standard music notation format supported by majority of the commercial music editing software.
Development of a Music Score Editor Based on MusicXML
Windows Presentation Foundation
Windows Presentation Foundation is Microsoft's next generation UI framework to create applications.
Real-time Networking
CAN Schedulability Analysis Refuted Revisted and Reviewed
A detailed description of the Controller Area Network protocol
Pushing The Limits of CAN
Scheduling Frames With Offsets Provides A Major Performance Boost
Performance Analysis of FlexRay-based ECU Networks
A case study analyzing FlexRay performance in Electronic Control Unit networks.
FlexRay Schedule Optimization of the Static Segment
Schedule optimization that minimizes the number of used slots is necessary to allow high flexibility for incremental schedule changes and for future automotive networks with a higher data volume
Greedy Heuristic for Dynamic Segment Scheduling
A greedy alternative to Integer Programming is proposed for dynamic segment scheduling.
Message Scheduling for the FlexRay Protocol: The Static Segment
Message Scheduling for the FlexRay Protocol: The Dynamic Segment
Signal and Speech Processing
Cepstral Analysis Synthesis on the Mel Frequency Scale
Analysis and synthesis using MLSA filters.
A Direct Approximation Technique of Log Magnitude Response
MLSA Digital Filter
A description of the Mel Log Spectral Approximation Filter
Approximation of Exponential Function in the Frequency Domain
Some calculations that I did to understand approximation of the exponential function in the Z-domain.
Coding Strategies and Standards
An overview of low bit rate coding techniques.
Sampling and Quantization
An overview of the steps involved in analog to digital conversion.
Application of Chirp Transform Algorithm to Muzzle Velocity Measurement
Speech Synthesis History
Software for Casecade Parallel Formant Synthesizer
A software formant synthesizer is described that can generate synthetic speech using a Computer.
From Text To Speech: The MITalk System
Part 1
From Text To Speech The MITalk System
Part 2
From Text To Speech: The MITalk System
Part 3
From Text To Speech: The MITalk System
Part 4
From Text To Speech: The MITalk System
Part 5
Review of Text-to-speech Conversion for English
Part 1
Review of Text-to-speech Conversion for English
Part 2
Review of Text-to-speech Conversion for English
Part 3
Review of Text-to-speech Conversion for English
Part 4
Hidden Markov Models
Theory and Implementation of Hidden Markov Models
Part 1
Theory and Implementation of Hidden Markov Models
Part 3
Theory and Implementation of Hidden Markov Models
Part 4
The Expectation Maximization Algorithm
Maximum likelihood with missing data
The HMM Toolkit
Chapter 1: The Fundamentals of HTK
The HMM Toolkit
Chapter 2: An Overview of HTK
The HMM Toolkit
Chapter 3: A Tutorial Example of Using HTK
The HMM Toolkit
Chapter 4 The Operating Environment
The HMM Toolkit
Chapter 5: Speech Input/Output
The HMM Toolkit
Chapter 6: Transcriptions and Label Files
The HMM Toolkit
Chapter 7: HMM Definition Files
The HMM Toolkit
Chapter 8: HMM Parameter Estimation
The HMM Toolkit
Chapter 10: HMM System Refinement
The HMM Toolkit
Chapter 12: Networks, Dictionaries and Language Models
The HMM Toolkit
Chapter 13: Decoding with HVite