Tag Archives: Text Search

Key learnings from building a “voice search” for hindi film songs

A couple of posts ago, I talked about the idea that “audio search” makes so much sense for a music app. We have been working behind the scenes looking at voice to speech technologies and evaluating them with a view to offer voice search in our app “Filmi Filmy”.

We are happy to report that we were completely wrong when we first thought of this – Since all of the song titles are entered in English but represent Hindi words phonetically eg: “O mere dil ke chain”, “Gata rahe mera dil” we think that we can use a voice to speech engine to take user inputs, turn them into phonetic English and use the English text as the search keys.

It turns out that is it much more elegant and natural to take the voice input “O mere dil ke chain”, render it as the hindi string “ओ मेरे दिल के चैन” and search for the hindi string in the database. One significant advantage to this is that it reduces the complexity of the phonetics completely. It does not matter if the “ke” is spelled as “key” anymore as in Hindi it will always be spelled as “के”.

The challenge of course is getting a database of film song titles entered in Hindi. Nearly all song databases have English transliterated titles – and may we add- not two of them spell the same song the same way. A healthy inheritance from English led and US led software is that from YouTube to the home grown Gaana nearly all the songs are in English.

We are happy to report that fortunately a bit of innovation and tons of persistence can solve this problem (we may not have a huge cash chest at Pariksha but we are certainly not short on tech coolness). One of our engineers figured out a way to use existing open-source tools to build hindi equivalents of the titles.

The results are spectacular, to say the least. Consider for example this song search using voice search with hindi titles v/s text search with English phrases below:

Text Search With English Phrases                                                Voice Search with Hindi Titles

We need to do a bit more work on the hindi song titles and improve the error handling on the search and this should be ready for public use. Now consider the scenario we had described earlier – Imagine slumping in a car after a long day and with no energy to type to search, all you have to do is say the song and voila the app will play it on your phone, ear-phone or connected blue-tooth speaker. Dare we say, it is not long before this will be a reality!

Flash v/s HTML5: It’s a war out there…is flash loosing out..?

Last week, Adobe released a preview of its HTML5 editor, “EDGE”. Early critics have pointed out the cumbersome UI and adobe lovers have pointed out the familiarity with flash development environment. It remains to be seen if Adobe will go on to dominate HTML5 tools given that for once they don’t control the HTMl5 standard (and may even be lagging behind on few counts) and till they acquired MacroMedia, they were indeed lagging behind even on website development tools (remember the Dreaweaver v/s GoLive no show) ?

However, one thing is certain – the impact of Apple refusing to support flash on its iPhone/iPAD devices has hurt the flash dominance of web rich media content.  Apple’s march towards global domination is led by necessities, apple has always been into developing product for its customers that supplies high intelligence at the cost of least power, and hence criticizing flash is a natural reaction.  What has not helped is adobe’s lack of aggressive evangelism of flash players on emergent android smart-phone and tablets. Instead, adobe may have tried to push away smart-phone OEMs with a licensing based business model for flash player which has further pushed users into adopting HTML5 as the lingua franca of mobile rich media.

One major concern in the apple camp is that they don’t believe that flash is open standard. In their own words – “just being widely available don’t make it open”. Apple believes that flash products are 100% proprietary and has been pushing for open web standards (w3c) in its products. Adobe counters by pointing out that most web users are missing on rich user experience since 75-90% websites do have flash content.  

Non availability of flash on iPAD has neither slowed down its adoption nor created any major frustration for its users. One major pitch for flash has been video streaming. However, with the modern h.264 streaming available via http streaming to iPhone/iPAD devices, usage of video has gone thru the roof even without flash support – just look at the traffic statistics from youtube, videmo, Netflix, facebook, abc, cbs, cnn, msnbc etc. This has further contributed to the growing feeling that flash is also “dispensable”.

Another significant reason for the rapid adoption of HTML5 v/s adaption of flash for mobile is that Flash was designed for PCs using mice, not touch screens using fingers. Most Flash websites need to be rewritten to support touch-based devices. If developers need to rewrite their Flash websites, why not use modern technologies like HTML5, CSS and JavaScript? Flash also drains more battery causing concerns from phone/tablet vendors.

So far, adobe has done promise, promise, promise but not deliver, deliver, deliver when it comes to Flash Player for the mobile.  With “EDGE” is adobe accepting a graceful “I am beaten” posture? Time will tell…