News for hackers. Stuff that matters.
Re:Speech Recognition Is Not Solved by adrianbg on Tuesday October 24, 2017 @03:50PM (#15544668)
You are correct that the problem is data. Kaldi is hard to use, but making it easier to use isn't as hard as getting good training data. Mozilla's project is a good start for some purposes. One flaw with it is that they're having people read sentences. When people read, they tend to speak more clearly than when they're figuring out what to say on the fly. This means models trained with Mozilla's data will tend to need people to speak extra clearly than eg. a model trained on conversational data.

(edits: spelling/grammar)

Re:Speech Recognition Is Not Solved by flukus on Tuesday October 24, 2017 @07:36PM (#15546136)
It's only a data issue if they're trying to reproduce google voice. Personally I got much better results from dragon naturally speaking 20 years ago than I get from google voice today, the cost was that you had to train it yourself first, but the benefit was it was trained for you, not "everyone". The later is the approach I'd prefer to see mozilla/OSS take.
Re:Speech Recognition Is Not Solved by adrianbg on Tuesday October 24, 2017 @08:03PM (#15546262)
That's fair. I think both approaches are useful in different situations. Mozilla seems to be focussing on Siri-like use-cases as opposed to dictation. Even for dictation, for many people having to train the system themselves is more work than they're willing to do. I'm sure what you want will exist eventually :)
Re:Speech Recognition Is Not Solved by pishpash on Tuesday October 24, 2017 @03:53PM (#15544701)
Oh it's not "hard" to get training data, you just need loads of money to buy the existing datasets.
Re:Speech Recognition Is Not Solved by dharma1 on Tuesday October 24, 2017 @03:59PM (#15544759)
or have more effective ways to collect tons of open source speech data. The Mozilla Common Voice project is really cool, but they should make it way easier for people to contribute.

Like, adding a mic button for voice search next to their main search toolbar on Firefox, and then ask for permission to use that data for research.

Re:Speech Recognition Is Not Solved by adrianbg on Tuesday October 24, 2017 @03:56PM (#15544735)
Hah sure. By "hard," I meant that it's the largest hurdle. And probably even the common research datasets aren't enough to give you results competitive with Google, etc. AFAIK Google uses its own hand-transcribed data.