User:Supisara: Difference between revisions

From XPUB & Lens-Based wiki
Line 6: Line 6:
'''a.) TextEdit + Spoken Content'''<br>
'''a.) TextEdit + Spoken Content'''<br>
[https://ubu.com/sound/lucier.html ''I Am Sitting in a Room]'' (1969) → I Am Sitting in a Room (2021), processed via transcription and text to speech:<br>
[https://ubu.com/sound/lucier.html ''I Am Sitting in a Room]'' (1969) → I Am Sitting in a Room (2021), processed via transcription and text to speech:<br>
* Part 1
:* System voice: English - Alex, Victoria, Whisper (novelty); Thai - Kanya
:* Speech variations: selection, items under the pointer, typing feedback
:* Video samples:
* Part 2
:* Audio extraction + overlay
:* Audio sample:


'''b.) Google Translate (Scan) + doodle'''<br>
'''b.) Google Translate (Scan) + doodle'''<br>

Revision as of 02:03, 6 October 2021

XPUB1 Special Issues

Special Issue 16

Experiments with vernacular processing methods:

a.) TextEdit + Spoken Content
I Am Sitting in a Room (1969) → I Am Sitting in a Room (2021), processed via transcription and text to speech:

  • Part 1
  • System voice: English - Alex, Victoria, Whisper (novelty); Thai - Kanya
  • Speech variations: selection, items under the pointer, typing feedback
  • Video samples:
  • Part 2
  • Audio extraction + overlay
  • Audio sample:

b.) Google Translate (Scan) + doodle
Image of text from multiple readers converted to:

c.) Google Docs + a linguistic pattern [group exercise on slow processing]