Comments for Okko in Speech http://www.okkoblog.com Working with speech and language technology Tue, 20 Jul 2010 09:13:37 +0000 hourly 1 http://wordpress.org/?v=3.0 Comment on This Goes to Eleven by Okko http://www.okkoblog.com/2010/07/20/this-goes-to-eleven/comment-page-1/#comment-312 Okko Tue, 20 Jul 2010 09:13:37 +0000 http://www.okkoblog.com/?p=195#comment-312 Thanks David! Thanks David!

]]> Comment on A More Optimistic Outlook on the Future of Speech by nsh http://www.okkoblog.com/2010/06/30/a-more-optimistic-outlook-on-the-future-of-speech/comment-page-1/#comment-294 nsh Thu, 08 Jul 2010 23:51:13 +0000 http://www.okkoblog.com/?p=187#comment-294 > What I mean by niches for speech are interesting applications that don’t compete > with mouse, keyboard or touch screen for user attention. Exactly, that's why I consider speech analytics that acts in parallel with usual user activity transparently listening for call, talk or meeting more perspective technology than IVR or dictation. I even started voting about that on blog but suprisingly it shows that way more readers still think that dictation and command & control are usable. Another such domain is language learning. > I would love to hear where you think the next major breakthrough for ASR > technology will come from. Well, it should be another source of information. Not necessary AI since I still believe that planes shouldn't flap wings. It might be WWW, then google will do that faster than anyone else ;) I took this new source idea from this nice post http://caterina.net/archive/001211.html > What I mean by niches for speech are interesting applications that don’t compete
> with mouse, keyboard or touch screen for user attention.

Exactly, that’s why I consider speech analytics that acts in parallel with usual user activity transparently listening for call, talk or meeting more perspective technology than IVR or dictation. I even started voting about that on blog but suprisingly it shows that way more readers still think that dictation and command & control are usable.

Another such domain is language learning.

> I would love to hear where you think the next major breakthrough for ASR
> technology will come from.

Well, it should be another source of information. Not necessary AI since I still believe that planes shouldn’t flap wings. It might be WWW, then google will do that faster than anyone else ;) I took this new source idea from this nice post

http://caterina.net/archive/001211.html

]]> Comment on A More Optimistic Outlook on the Future of Speech by Okko http://www.okkoblog.com/2010/06/30/a-more-optimistic-outlook-on-the-future-of-speech/comment-page-1/#comment-289 Okko Mon, 05 Jul 2010 19:05:47 +0000 http://www.okkoblog.com/?p=187#comment-289 Agree - even good practices are the cause of the stagnation. We know IVR systems are awful to use compared to web pages (or flashy iPhone apps), but by giving their awfulness a certain pattern, we can work around technological limitations. What I mean by niches for speech are interesting applications that don't compete with mouse, keyboard or touch screen for user attention. These are battles bound to be lost. Fancy voice interfaces will always come second to more immersive or efficient input methods. I would love to hear where you think the next major breakthrough for ASR technology will come from. Agree – even good practices are the cause of the stagnation. We know IVR systems are awful to use compared to web pages (or flashy iPhone apps), but by giving their awfulness a certain pattern, we can work around technological limitations.

What I mean by niches for speech are interesting applications that don’t compete with mouse, keyboard or touch screen for user attention. These are battles bound to be lost. Fancy voice interfaces will always come second to more immersive or efficient input methods.

I would love to hear where you think the next major breakthrough for ASR technology will come from.

]]> Comment on A More Optimistic Outlook on the Future of Speech by nsh http://www.okkoblog.com/2010/06/30/a-more-optimistic-outlook-on-the-future-of-speech/comment-page-1/#comment-279 nsh Thu, 01 Jul 2010 00:45:27 +0000 http://www.okkoblog.com/?p=187#comment-279 I kind of disagree that it's just practice issue. The whole experience in bringing up ASR products leads to the the conclusion that technolgy is not there yet. Users can't operate with 90% success rate, most applications require 99.999%. But I consider this stagnation as a delay before major breakthrough in the technology, so right now is a perfect time to start with ASR and catch the wave that will appear soon. I kind of disagree that it’s just practice issue. The whole experience in bringing up ASR products leads to the the conclusion that technolgy is not there yet. Users can’t operate with 90% success rate, most applications require 99.999%.

But I consider this stagnation as a delay before major breakthrough in the technology, so right now is a perfect time to start with ASR and catch the wave that will appear soon.

]]> Comment on Quick Voice Prompts with Google Translate TTS Service by Facebook Like Site http://www.okkoblog.com/2010/01/12/quick-voice-prompts-with-google-translate-tts-service/comment-page-1/#comment-233 Facebook Like Site Sun, 06 Jun 2010 01:09:58 +0000 http://www.okkoblog.com/?p=149#comment-233 Nice post. Have u heard about the iPad hack? Kinda random but lol why not. Nice post. Have u heard about the iPad hack? Kinda random but lol why not.

]]> Comment on News Redux & Building VoiceGlue by forexs http://www.okkoblog.com/2007/12/04/news-redux-building-voiceglue/comment-page-1/#comment-217 forexs Thu, 27 May 2010 15:26:28 +0000 http://okkoblog.com/blog/?p=33#comment-217 thanks a lot for this wonderful article thanks a lot for this wonderful article

]]> Comment on SpinVox, Voice-to-Text and Some Terminology by philippine tv online http://www.okkoblog.com/2010/01/18/spinvox-voice-to-text-and-some-terminology/comment-page-1/#comment-22 philippine tv online Wed, 17 Feb 2010 19:44:34 +0000 http://www.okkoblog.com/?p=156#comment-22 I used osx's 'text to mp3' to do the voice within my Youtube video. So trust me guys, voice things work great, you should use them too! One problem I had was when it tried to pronounce some 'fake' words/ sounds like 'woosh', but with practice it's easy :-) I used osx’s ‘text to mp3′ to do the voice within my Youtube video. So trust me guys, voice things work great, you should use them too! One problem I had was when it tried to pronounce some ‘fake’ words/ sounds like ‘woosh’, but with practice it’s easy :-)

]]> Comment on SpinVox, Voice-to-Text and Some Terminology by Okko http://www.okkoblog.com/2010/01/18/spinvox-voice-to-text-and-some-terminology/comment-page-1/#comment-19 Okko Sun, 31 Jan 2010 19:51:30 +0000 http://www.okkoblog.com/?p=156#comment-19 Thanks for those links. That study slipped by me. I'm very curious to see where this is going. Some obvious questions are how accessible and pervasive voice transcription will become. Will there be a healthy developer base (voice technologies always suffer from having a small, somewhat esoteric one). What about "real" web APIs, leveraging this stuff for mash ups like smart ad placements in video, 3rd party calendar plug-ins, etc.. How to enable real international market penetration is also big question. English speaking ones appear reaching a good level of maturity. I've <a href="http://www.okkoblog.com/2008/05/05/internationalization-and-speech-technologies/" rel="nofollow">previously written</a> about the fact that there is no long tail in speech and language technology development. The buy-in costs per market/language remain the same, regardless of market size. Capital per market however varies greatly. This could be a real show stopper. Thoughts? Thanks for those links. That study slipped by me.

I’m very curious to see where this is going. Some obvious questions are how accessible and pervasive voice transcription will become. Will there be a healthy developer base (voice technologies always suffer from having a small, somewhat esoteric one). What about “real” web APIs, leveraging this stuff for mash ups like smart ad placements in video, 3rd party calendar plug-ins, etc..

How to enable real international market penetration is also big question. English speaking ones appear reaching a good level of maturity. I’ve previously written about the fact that there is no long tail in speech and language technology development. The buy-in costs per market/language remain the same, regardless of market size. Capital per market however varies greatly. This could be a real show stopper.

Thoughts?

]]> Comment on SpinVox, Voice-to-Text and Some Terminology by James Siminoff http://www.okkoblog.com/2010/01/18/spinvox-voice-to-text-and-some-terminology/comment-page-1/#comment-18 James Siminoff Sun, 31 Jan 2010 17:23:39 +0000 http://www.okkoblog.com/?p=156#comment-18 You should check out, http://www.techcrunch.com/2010/01/28/phonetag-voice-to-text-86-percent-accurate-google-voice/. You will probably also be interested in the study, http://www.scribd.com/doc/26017529/Accuracy-of-Voicemail-To-text-Services. I think that this will be a very interesting market to follow in the next few years. You should check out, http://www.techcrunch.com/2010/01/28/phonetag-voice-to-text-86-percent-accurate-google-voice/. You will probably also be interested in the study, http://www.scribd.com/doc/26017529/Accuracy-of-Voicemail-To-text-Services.

I think that this will be a very interesting market to follow in the next few years.

]]> Comment on Speaking Piano by Okko http://www.okkoblog.com/2009/12/31/speaking-piano/comment-page-1/#comment-17 Okko Fri, 08 Jan 2010 21:16:12 +0000 http://www.okkoblog.com/?p=71#comment-17 Let's do it! Let’s do it!

]]>