Nayana Raj's repositories
accent-recognition-across-language-families
Final project for the course Analyzing Large Speech Corpora with Machine Learning, Fall 2018.
indicnlp_corpus
Description Describes the IndicNLP corpus and associated datasets
indicstemmer
experimental malayalam stemmer
jsPsych
A JavaScript library for creating and running behavioral experiments in a web browser
MLP_Word_Segementation
This a code written for training and evaluating Sandhi Splitter or Word segmentor in Dravidian languages. The dataset provided here is for Malayalam, however any langauge dataset can be used. This system tries to classify each and every character in a word to split point and non split point based on the character contexts.
natural-speech-versus-automated-speech
Comparison of Natural Speech and Automated Speech Generated by gTTS using Duration Models
Stem-Extenders-in-Malayalam
Mini-project for the course Natural Language Understanding, Fall 2020.
praat-py
From my PhD days: Praat-Py is a custom build of Praat, the computer program used by linguists for doing phonetic analysis on sound files, to allow for scripts to be written in the Python programming language, rather than in Praat's built-in language.