On the language barrier and AI.

Natively, I speak Telugu. I've learnt to speak Hindi and English. I currently live in a city, where most speak Marathi. I used to live in a city where most spoke Tamil. And I'm not atypical. Most Indians cross state lines over the course of their lives, for work or other reasons. And the language barrier is the biggest problem while doing so.
Personally, even though I lived in Chennai for over 6 years, I still can't speak or understand Tamil and Marathi might as well be Arabic to me, even after living in Pune for just over an year. (I'm clearly not trying hard enough to learn the language.) Unlike me, most people who stay for a long (1+ year) at a location learn the local language, because it makes day-to-day life easier. But what about travelers? What about those who stay for a short period of time? What about those not educated in a common language?

You can argue that a majority of Indians can speak and understand Hindi. Actually, No. And no, the majority of Indians don't speak or understand English either. This is what I meant by having a common language to communicate in. What do we do now?

Well, taking a small detour, Google Translate and the Chrome browser do a pretty good job at translating content from one language to another. There are also options available to spell the translated word/text, if I'm not wrong. What if I could instead say something that Google could then transcribe and then translate. This is where I think AI/ML can help.

Imagine this. There are two people talking, in two different languages. An AI is handling the transcription and translation. This AI can be a simple app on a mobile phone that simply records the audio and outputs a text, in a language of choice. It could have a Google Glass like interface where the user's words appear as subtitles in the language of choice. Or it could be noise-canceling headphone that repeat the other person's words in the language of choice. You choose which would provide the best user interface. I would personally choose the first because it's easier to prototype and release.

If I'm not wrong, AI isn't good at transcribing languages other than English yet. The Chinese are also working on this problem, specifically Alibaba. Otherwise, I don't know if an AI exists that can transcribe Hindi or Tamil or Marathi. Developing one such AI would dramatically increase communication between the people across state and national borders.

I'm going to put this in the `Someday in the future` box of things that I plan to work on. Until then.

Popular posts from this blog

Arxiv author affiliations using Python

So, I wanted to get author affiliation information from papers on arXiv. arXiv provides with an API to bulk query their database and get information. Following that, I look for the attribute 'arxiv:affiliation' in the html data. Here's the code - import urllib from BeautifulSoup import BeautifulStoneSoup   url = 'http://export.arxiv.org/api/query?search_query=all:astro&start=0&max_results=1000'   data = urllib.urlopen(url).read() soup = BeautifulStoneSoup(data) #print(soup.prettify()) #list = soup.findAll('arxiv:affiliation') #for i in range(len(list)): #        print list[i].contents   test = [tag.string for tag in soup.findAll('arxiv:aiffiliation')] Now, the problem I'm having is that I'm getting affiliation of all authors which I want to split into sets of affiliations of authors of a paper, which I'm stuck on at the moment. Once I get that part, I can move on to the next part of this pet project, displaying these
Read more

Farewell to Enthought

I started my professional career at Enthought , at the Pune office in India, on Feb 29, 2016. Over the course of eight long years, I spent time at the Austin office in the US, the Cambridge office in the UK, and I worked remotely from India. I was let go on March 27, 2024 . I had an unbelievably great time. I had three amazing mentors - Pankaj Pandey, Senganal Thirunavukkarasu, and Mark Dickinson. Pankaj mentored me in my first year at Enthought. I started paying attention to the craft of software after working with him. Senganal started mentoring me in my second year at Enthought, and continues to mentor me, even after the both of us have moved on from Enthought. He instilled professionalism in me, ensuring that the code I wrote produced precise scientific results, and that I tackled the known unknown aspects of a project first, to ensure timely communication about project progress. I was eager to manage people at the time and Senganal made me realize that I didn't want to manage
Read more

Elementary (particle physics), my dear Watson

Ground Control to Major Tom:  Shruti Patel checking in. Since my dear friend and fellow-physicist Rahul Poruri is homeward bound, and shall remain there for a week, I'm stepping in to continue his tradition of daily posts to Astronut . Even as I write, I'm not quite sure what this post is going to be about, so please forgive me for occasional rants and digressions.  By the way Rahul, I totally resent you for the name of this blog- I'm never going to start my own blog because there's no way I'll come up with a name as cool as Astronut! For now, I shall try and be happy with being a guest writer! Before I begin, a little bit on who I am and what I do; so that you can trust that my general views on science- particle physics in particular- are not entirely baseless. I graduated with a masters in Physics from IIT Madras in July this year, and I'm currently working towards (an eventual) PhD with the Theory Group at the Deutsches Electronen-Synchrotron (DESY)
Read more