Mlphon: A Multifunctional Grapheme-Phoneme Conversion Tool Using Finite State Transducers

 Posted on September 20, 2022  |  Kavya Manohar

The Mlphon tool I had been working on, for the past couple of years was extensively expanded as part of my research work at College of Engineering Trivandrum. A detailed presentation of the phonemic features of Malayalam, their incorporation as a sequential ruleset in the form of finite state transucers, a quantitative evaluation of the applications of the tool are now available in the article, published by the open access journal, IEEE Access. [Read More]
malayalam  speech  g2p  p2g  publication 

Mozhi Malayalam TTS powered by Mlphon and Mlmorph

 Posted on May 25, 2022  |  Kavya Manohar

Krishna Sankar recently developed a Malayalam - English bilingual Text to Speech System, Mozhi. Check the web demo page and play around with your choice of words and listen to the natural speech it produces. Krishna has set a future goal of understanding the emotional content of the text and read it out accordingly. This is expected to make the application suitable for audio books. Generating audio for arbitrary speaker with very few training samples is another area he plans to work on. [Read More]
malayalam  speech  tts  mozhi 

Publishing Malayalam Speech Recognition Model

 Posted on October 19, 2021  |  Kavya Manohar

Malayalam speech recognition model trained on various openly available speech and text corpora using Kaldi toolkit is now released here. It is now available for testing on the Vosk-Browser Speech Recognition Demo website. This Malayalam model can be used with Vosk speech recognition toolkit which has bindings for Java, Javascript, C# and Python. A speech recognition architecture that works best in scenarios of limited speech data availability is called a pipeline model, where it is composed of an acoustic model, a language model and a phonetic lexicon. [Read More]
malayalam  speech  vosk  kaldi  asr 

The language of infinite words

 Posted on March 1, 2021  |  Kavya Manohar

I wrote this article for submission to a popular science writing competition by the Department of Science and Technology. Here is my research story, which did not make to grab the award. The story is based on our research on the morphological richness of Malayalam language. How many words are there in your language? How many of them do you know? Can you find all those words in a dictionary? [Read More]
malayalam  speech  morphology  linguistics  conference  tsd 

Text Speech and Dialogue: TSD 2020

 Posted on September 12, 2020  |  Kavya Manohar

I presented a paper on Quantitative Analysis of the Morphological Complexity of Malayalam Language at 23rd International Conference on Text, Speech and Dialogue: TSD 2020, Brno, Czech Republic, September 8–11 2020. The year being 2020, the entire conference happened in remote participation mode. Conference proceedings and pre-recorded presentation videos were made available to the participants and we discussed it over online zoom sessions. It was a novel experience and I am super excited about how I got feedbacks and ideas to work on, even after the live sessions. [Read More]
malayalam  speech  morphology  linguistics  conference  tsd 

Releasing Malayalam Speech Corpus

 Posted on August 25, 2020  |  Kavya Manohar

Originally Published in SMC Blog SMC announces the release of Malayalam Speech Corpus (MSC). It is the repository of curated speech samples collected using MSC web application. Speech samples are selected on the criteria that they have at least 3 positive reviews. MSC is a project launched by SMC to crowd source Malayalam speech samples from any contributor who can read out sentences and record them as speech samples. The MSC web app has provisions for recording voices and reviewing them. [Read More]
Speech Recognition  Malayalam  Corpus  Speech 

Phonetic description of Malayalam consonants

 Posted on January 18, 2020  |  Kavya Manohar

The orthography (system for writing a language) of Malayalam is considered phonemic in nature. It means the graphemes (written symbols) correspond to the phonemes (significant spoken sounds) of the language. But the correspondence between graphemes and phonemes is not precisely one-to-one. The pronunciation of graphemes can depend on its position in a word (word beginning, middle or end) and its proximity to other graphemes. It was two years back, I started to work on a grapheme to phoneme conversion tool for Malayalam. [Read More]
Malayalam  Phonetics  Speech  Grapheme  Phoneme