February, 2005

  • Rob's Speech Stuff

    TTS navigation

    • 1 Comments
    Haha. Sushant, this is a fascinating problem. SAPI has some inherent TTS navigation capabilities, but it looks like you need a little bit more. The problem's certainly soluble (I have one approach in mind). I'll try to post my thoughts later in the week...
  • Rob's Speech Stuff

    Text Navigation

    • 3 Comments
    Sushant, s orry I missed your comment . I’ve re-posted it on your behalf – hope you don’t mind. Can you post another comment to explain what you mean by text navigation? (e.g. do you mean VCR-style controls for TTS, selection of insertion points for dictation...
  • Rob's Speech Stuff

    Choosing speech API features

    • 3 Comments
    James makes a good point that limiting API features to known examples of applications potentially lowers the ceiling on how well an API can adapt to unanticipated needs. I think he's right. But it's only one factor. When multiple new features are competing...
  • Rob's Speech Stuff

    Speech platforms

    • 10 Comments
    Since a few different speech technologies were mentioned in the comments, I thought it might be useful to summarize the speech platform technology we currently provide. Windows Windows XP, Tablet and 2003 all include: SAPI 5.1: the COM API for use by...
  • Rob's Speech Stuff

    Phoneme segmentation

    • 7 Comments
    In a recent comment, James Salsman wrote “SAPI 4.0a had phoneme segmentation” and he asks that we put it back into our newer APIs. (You can see more about SAPI 4 here ). It’s been a long time since we made an API with this functionality. I’m curious to...
  • Rob's Speech Stuff

    Thoughts on speech API topics

    • 7 Comments
    I've been chatting with quite a few people on the team this week about what categories of posts would be interesting and relevant (and inserting "that's a great idea, you should blog it" into each conversation :-). I'm thinking these three broad categories...
  • Rob's Speech Stuff

    about me

    • 2 Comments
    Like the title says, my name's Robert Brown. I'm a Program Manager at Microsoft, working on speech technologies - in particular, the APIs. I expect this log to be about both program management and speech. We'll see if I predict correctly. What's speech...
Page 1 of 1 (7 items)