Help Kanru Hua with revising the experimental Arpasing recording script

Discussion in 'Projects & WIPs' started by Kiyoteru, Aug 30, 2017.

  1. Kiyoteru

    Kiyoteru Local Sensei / Kuya Supporter Defender of Defoko

    Messages
    2,126
    Likes Received
    2,935
    Trophy Points
    157
    Original blog post: https://webhost.engr.illinois.edu/~...g-the-experimental-arpasing-recording-script/
    VocalSynth.Space post: https://vocalsynth.space/d/62-help-me-with-revising-the-experimental-arpasing-recording-script

    [hr]

    Hello folks,

    After 300 CPU-hours of intense computation, a new recording script for Arpasing has been generated.

    Unlike the lists you've seen before, this one consists of actually meaningful words and phrases selected from a small subset of public-domain books from Project Gutenberg, yet it is different from CMU Arctic (which is also based on Gutenberg) in that the new Arpasing script is designed for singing synthesis. You can take a glimpse at the first few lines,
    1. was Matthew's consolatory rejoinder
    2. he stood before the wide opening
    3. we shall begin our researches here
    4. with his usual craving on him
    5. but this little line of dancing men
    Theoretically, this new script can match the current 220-line script performance-wise, using its first 65 lines only (though the total number of syllables remains roughly the same); on the top of that, the rest 135 lines should double the coherency.

    But speech synthesis is all about experiments. Before rushing into the recording studio, I'd like to focus on improving the ease of pronunciation by taking out phrases that are hard to read even to native speakers. To keep the selection as unbiased as possible, I kindly request users of Arpasing and people with an interest in the matter to review and comment on the draft:

    Google Spreadsheet

    Thanks for your support!

    [hr]

    TL;DR Please add 1 to rows you think are hard to read, and use the Google Sheets comment feature to leave any additional feedback. Please do not vandalize the spreadsheet.
     
  2.  
  3. WinterdrivE

    WinterdrivE Ritsu's Renegades Defender of Defoko

    Messages
    48
    Likes Received
    258
    Trophy Points
    67
    Wait, is this intended to be read with every syllable the same length? Cuz these strings (eg, the first one) are upwards of 10 syllables long.
     
  4. Kiyoteru

    Kiyoteru Local Sensei / Kuya Supporter Defender of Defoko

    Messages
    2,126
    Likes Received
    2,935
    Trophy Points
    157
    ...Wow, that does seem a little too long. That'd be useful feedback to leave.
     
  5. WinterdrivE

    WinterdrivE Ritsu's Renegades Defender of Defoko

    Messages
    48
    Likes Received
    258
    Trophy Points
    67
    Also, i've noticed that possessive 's seems to always be transcribed into arpabet as "eh s" which its not actually pronounced that way
     
  6. Damien

    Damien Wannabe Worker Supporter Defender of Defoko

    Messages
    134
    Likes Received
    1,091
    Trophy Points
    108
    I would understand if this is intended to be spoken, but sung, ehh. WinterdrivE has a good point up above. (also pronunciation of certain words vary for me compared to the phonetics)
     
    Kiyoteru likes this.
  7. Kiyoteru

    Kiyoteru Local Sensei / Kuya Supporter Defender of Defoko

    Messages
    2,126
    Likes Received
    2,935
    Trophy Points
    157
    If not in the spreadsheet, I'd advise leaving these replies over on the VocalSynth Social thread, where Kanru will see them.
     
  8. Kiyoteru

    Kiyoteru Local Sensei / Kuya Supporter Defender of Defoko

    Messages
    2,126
    Likes Received
    2,935
    Trophy Points
    157
  9. WinterdrivE

    WinterdrivE Ritsu's Renegades Defender of Defoko

    Messages
    48
    Likes Received
    258
    Trophy Points
    67
    I'm glad these new lists seem to have fixed the 150 year old obscure academic vocabulary problem.
     
    Kiyoteru, VocAddict and Damien like this.

Share This Page