Automatic generation of Tamil lyrics for melodies

Paper details: “Automatic Generation of Tamil Lyrics for Melodies.”
Authors: Ananth Ramakrishnan A., Sankar Kuppan and Sobha Lalitha Devi

I was browsing through the schedule page of a workshop on: “Computational Approaches to Linguistic Creativity”, 2009. I came across this title – “Automatic generation of Tamil lyrics for melodies” and was quite fascinated by it. I am perennially suspicious about works on such sci-fi topics and their efficiency levels. Nevertheless, I was eager to read it. Back then, the workshop did not happen and the paper was not accessible for download. Now, it is, and I finally got a chance to have a look at it (Interested? download-here)

So, as the name indicates, this explains a system which generates lyrics for a given melody, automatically. They did this for Tamil. There was a kind of general overview of the process and a mention about related work. There was this reference to a work about a “poetry generation system” !! I was shocked to a considerable extent. Most of human poetry itself is unreadable and sometimes crappy. We think about Poetry generation! Man’s imagination indeed roams freely in thin air 🙂 There was even this reference to some work on “lyric generation strategies” and I thought – “Oh! this is not sci-fi then, if so many are working in this direction!” 🙂

Coming to the paper, the process of lyric generation involves 2 steps:
1. Syllabic pattern generation
2. Identifying a phrase matching this pattern, as well as satisfying other word/sentence/rhyming requirements.

For the first part, they used a notation called KNM. K stands for Kuril-Short vowel, N for Nedil- Long vowel and M for Mei-Consonants. Taking their own example, the word thAmarai will be broken as “thA-ma-rai” and will be labelled as NKN. To generate such patterns for a given melody, they have used Machine Learning (specifically the Conditional Random Fields aka CRFs) to train a system to learn these patterns. The system was trained with sample film songs and their lyrics as input (and… I got doubts about the size of data they trained with..). This trained model is used to then label a given melody with a syllabic pattern. This pattern is then given to a sentence generation module which generates a sentence that satisfies the following conditions:
1. Words should match the syllabic pattern
2. Sequence of words should have a meaning.

This is like a baseline level work and they mention about the ways they plan to improve their system in future. They also plan to experiment more with different strategies as well as different domain data sets. Finally, they mention my “sci-fi” idea of poetry generation again 🙂
This is an extra brief summary about it. For more details, go on and visit it online.

Published in: on June 11, 2009 at 10:27 am  Comments (13)  

The URI to TrackBack this entry is:

RSS feed for comments on this post.

13 CommentsLeave a comment

  1. goodone………….

  2. !

  3. Certainly an interesting paper! In fact, I can imagine an excellent funding – guaranteed for this research group for the next few years. In fact, it’d become the best non-state funded project ever in Indian academic history! You know who those funding agencies would be :-).

    Now to your _“sci-fi” idea of poetry_ the idea is not new. Such tools exist. On a related note, when hot discussions were going on the sense and (more) non-sense in Po-Mo-scholarship a “post-modern generator” was developed.

    Do read the complete, right to the bottom, before coming to quick conclusions 🙂


  4. endukandi ituvanti panikiraani researchlu anni… korakaraanikoyya kaakapotee…tindi pedutundaaa, gudda istundaa:D…

  5. Quite interesting! Thanks for sharing it.
    I am not very knowledgeble in music but I thought we can map durations of notes to KN sequence. So, given a sequence of notes, we can directly get the KN sequence. Not sure why we need to go for learning techniques for this.
    And regarding Edit-distance matching: I would think for the given pattern NKN, we can list words that match NKKK, KKKN – not NKK and KKN.
    The above thoughts are purely based on my understandng about telugu meter.

  6. Firstly, nice to see so many comments.
    @Vamsi: 🙂 No comments. Not all research is for societal benifit, perhaps.
    @Paruchuri garu: Thanks. Will chek out.
    @Kameswara rao garu: I think the song will be coming and we need to generate KN sequence. Is there a way in which one can generate Notes directly from the song..automatically?

  7. really Interesting

  8. Sowmya garu,
    What I understood is that the input is a melody (basically the tune). This is nothing but a sequence of notes in ABC notation.
    By “song”, if you meant the actual song with music+lyrics, I don’t think that is the input. The whole point is to automatically generate (new)lyrics for a given tune (that might not have any lyrics at all) right?

  9. Awesome! – will be very interesting to see how it comes to life… May be in future – there will be no need for the so called “kau”s… A Human Poet’s brilliant (or not so brilliant) mind will eat dust I guess…just kidding….any news for the same in “telugu”

    On a side note – “kooDu peDutundA guDDa peDutundA” anna vErE vamSI gAru – “idi” “Edi” peTTAlO cebitE bAgundEdi.. 🙂

  10. Some very interesting points raised here, which has got me thinking!

  11. Hello Sowmya,

    Surprised (& happy) to see a write-up on our paper. I am the author of the said paper and if you want to know more details, please feel free to write to me.


  12. Hmm. Is it true? 🙂

  13. Next time I read a blog, Hopefully it doesn’t disappoint me as much as this particular one. After all, I know it was my choice to read through, but I actually believed you would have something useful to say. All I hear is a bunch of crying about something you could fix if you weren’t too busy looking for attention.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: