Understanding non-American accents

Why the focus on ‘Indian’? Well, by far the biggest issue for me was in getting Siri to understand my accent. People who know me claim that I don’t have that thick an accent, but that’s not what Siri ‘tells’ me.

On the plus side, Siri is subtly training me to have a more ‘American’ voice. She highlights words she has trouble understanding in blue, so you can quickly figure out what words one is consistently mispronouncing, or pronouncing with a thick accent. ‘Paragon’ was totally off, for instance!

Your wish is my command – but be QUICK

It’s almost impossible to dictate text messages through Siri – at least for me. I tend to pause just a little too long between sentences, and Siri needs you to know exactly what you want to say before you start dictating.

In fact, I ended up using Voice Notes to record quick notes for myself, when I’d have preferred to dictate them through Siri. On the plus side, you can use earphone controls to record/pause Voice Notes, for some quick eyes-on-the-road note taking.

Ethnic language models

The language models need more work, and I won’t be surprised if there are people hard at work creating ethnicity-oriented speech models. Guessing the ethnicity shouldn’t be that hard to do, given all the clues Apple has – the name of the person, their entire addressbook, and recorded voice samples. These samples can be compared to aggregate training data collected from virtually every country on the planet.

The holy grail, of course, would be a trained model on a per-person basis, but I wonder if they have the compute resources and data volume, on a per-person basis, to make that happen effectively.

To the future!
Amit

Chris Dixon wrote a great post in Jan '10 called 'The next big thing will start off looking like a toy' (http://cdixon.org/2010/01/03/the…). Siri is a great example of this.

The leading indicator that Siri will be amazingly successful is that people are having fun with it – and it's not breaking.

Let's take the simple use case of 'Hey Siri, tell me a joke.' Consistently answering this with a humorous response requires

• Speech recognition (or at least noise-free recording)
• Cloud-based interpretation and response
• Believable text-to-speech

(The last one is very important, by the way. Apple has spent decades getting text-to-speech right, complete with stresses, tones and nuances (har har). This is paying rich dividends now)

Each time someone demoes the 5 funny Siri use-cases to their friends, the system becomes smarter, but more importantly, the technology gets humanized. More people will use it because it's like a toy.

In fact, I don't have an iPhone 4S right now. Guess what – I've started using the clunky Voice Control on my iPhone 3GS these days, because I somehow trust it'll work now. And it does!

Also in Jan '10, Fred Wilson wrote a dictated blog post using an Android phone (http://www.avc.com/a_vc/2010/01/…). I'm sure he, and other long-time android users all over, are looking at iPhone users quizzically, and wondering what the fuss is. After all, isn't this merely Voice Control plus some Text-to-Speech thrown in?

The difference is – Android's voice capabilities were a feature, Siri is a toy. And that makes all the difference.

Amit

Post on Quora