› Forums › Speech Synthesis › Evaluation › Audio in Qualtrics?
- This topic has 6 replies, 4 voices, and was last updated 4 years, 4 months ago by Rita F.
-
AuthorPosts
-
-
March 31, 2020 at 15:52 #11070
I have created a Qualtrics account and started building a survey, but I don’t really see any audio features at all, in any templates or in the ‘build a project from scratch’-section. Could someone maybe point me in the direction of that? Thanks 😉
-
March 31, 2020 at 16:27 #11071
You need to upload media to your library first, then -> https://www.qualtrics.com/support/survey-platform/survey-module/editing-questions/rich-content-editor/insert-media/
-
April 1, 2020 at 18:25 #11081
Thanks, that works!
It was mentioned in lectures and labs that audio need to be converted to mp3. But I have been able to build, publish and run a small test with 16kHz wav-files. Are there any reports as to what the problem with wav-files might be? -
April 2, 2020 at 09:41 #11085
Qualtrics might convert them to mp3 silently (certainly some platforms do) – check in a browser by taking your completed test as a subject.
The main problems with using wav files on the web are
- They are larger than mp3 – not a problem here: we care about quality not size
- Some browsers, notably Safari, will not play wav files
-
April 10, 2020 at 14:51 #11140
One of my synthesized voices has a pretty low volume and I am afraid that it might influence evaluation. Is there any way to increase its volume now?
-
April 10, 2020 at 15:13 #11141
It is a good idea for each voice to have approximately the same loudness (which is a perceptual property). You can apply a global scaling factor to all the synthetic waveforms for a voice using sox:
% sox -v 3.5 in.wav out.wav
Choose a volume scaling factor (3.5 in the above example) by ear, then apply the same scaling to all waveforms from that voice. Be careful not to clip, and so it’s good practice to inspect the waveforms afterwards (e.g., in Praat) to check for that. You shouldn’t need to adjust the volume too precisely to achieve sufficiently uniform perceived loudness across voices.
It’s always safer to scale down rather than up, but if one voice is very quiet then scaling that one up is fine.
You might be tempted to normalise (i.e., automatically apply the maximum scaling-up that is safe without clipping) using sox, but doing that for individual files can result in varying perceptual loudness because the phonetic content will vary utterance-to-utterance. Loudness is not the same as amplitude!
-
April 10, 2020 at 16:34 #11144
Great, it works. At first it returned:
sox WARN wav: Premature EOF on .wav input file
fixed by changing output name.
I got a warning about clipping above certain scaling values so didn’t need to check it in praat.
sox WARN sox: `general1_2.wav' output clipped 732 samples; decrease volume?
-
-
AuthorPosts
- You must be logged in to reply to this topic.