Activity
From 08.06.2016 to 07.07.2016
07.07.2016
- 13:30 Task #3844 (Resolved): Analyze utterances with phonetically incorrect phoneme
- Auditory analysis of the male speaker yielded more favourable results than for the female. Details are attached as a ...
04.07.2016
- 23:11 Task #3949 (Assigned): G-P conversion of foreign words
- 23:02 Task #3972 (Closed): Use formants instead of MFCCs in join cost computation
- Use formants from #3971 and replace MFCCs.
Compute both static and dynamic contours around a concatenation point (... - 22:43 Task #3971 (Closed): Praat script to compute formants
- Please attach a Praat script to compute formants from speech waveforms.
More specifically:
* compute formant freq... - 22:32 Task #3970 (Closed): Formant-based join cost computation
- _Parent task for experiments with formant-based parameters for join cost computation_
A hypothesis is that continu...
01.07.2016
- 13:08 Task #3941 (Resolved): Create synthesis logs for corpora with altered prosodic words
- After a week of troubles, I have finally managed to get the experiment working.
Resulting logs are stored to @Exper...
30.06.2016
- 12:41 Task #3965 (Closed): EMA - Radka Mašková
- _Parent task for EMA based experiment with Radka Mašková_
24.06.2016
- 15:42 Task #3709 (Closed): Merge ASF files (segmentations) and SNT files (annotations)
- 15:41 Task #3709 (Resolved): Merge ASF files (segmentations) and SNT files (annotations)
- *Summary*
Voices wih merged ASFs:
* Czech voices: AJ, JS, KI, MR, SK, TJ
* Slovak voice: MM
ASF file for the ...
23.06.2016
- 16:48 Task #3844 (Assigned): Analyze utterances with phonetically incorrect phoneme
- The same as before, but now for _male_ voice (Jan, spkr_AJ) - data put as attachment on [[Task_3688|wiki]].
- 16:45 Task #3935 (Closed): Add classifier scripts to SVN
- 12:28 Task #3922 (Closed): Synthesize utterances with phonetically incorrect phoneme realizations - voice Jan
- Data were put to [[Task_3688|wiki]].
21.06.2016
- 13:33 Task #3844 (Resolved): Analyze utterances with phonetically incorrect phoneme
- The second round of auditory analyses did not reveal any new information. The conclusions and recommendations from th...
- 11:30 Task #3949 (Closed): G-P conversion of foreign words
- Basic forms of foreign words are typically transcribed correctly, but the transcription (and hence the synthesized pr...
17.06.2016
- 08:28 Task #3922: Synthesize utterances with phonetically incorrect phoneme realizations - voice Jan
- Update: after diphone list fixes, new images are stored in @Experiments/NoUnitSubsts/spkr_AJ_rev652.[baseline/nosubst...
16.06.2016
- 16:30 Task #3941: Create synthesis logs for corpora with altered prosodic words
- File *pros_words.py* contains function *set_pwords( unit_list, ver=1 )* where
* *unit_list* is a list of units == ...
15.06.2016
- 10:23 Task #3944 (Closed): Commit changes based on user(s) logged in/out
- Would it be possible (and not too difficult) to trigger commit of ASF changes when all users working on the given lan...
13.06.2016
- 10:53 Task #3941 (Feedback): Create synthesis logs for corpora with altered prosodic words
- I will need a python script assigning new _PWord_ tags to a sequence of phones (or preferably ASF units). Then I can ...
- 10:35 Task #3922 (Resolved): Synthesize utterances with phonetically incorrect phoneme realizations - voice Jan
- Both baseline (with substitutions) and new (no substitutions) were copied to ARTIC data, path: @Experiments/NoUnitSub...
- 10:04 Task #3813 (Closed): Submit a paper for INTERSPEECH2016 (D)
- Accepted :-)
- 09:30 Task #3809 (Closed): Submit a paper for INTERSPEECH 2016
- Unfortunately rejected ...
10.06.2016
- 10:44 Task #3935 (Resolved): Add classifier scripts to SVN
- There were several modification of the scripts carried out. Here I describe them with a few warnings:
*JSON output...
09.06.2016
- 12:57 Task #3922: Synthesize utterances with phonetically incorrect phoneme realizations - voice Jan
- Nosubst image of the voice is needed for the last step of synthesis.
- 12:56 Task #3941 (Closed): Create synthesis logs for corpora with altered prosodic words
- Can you create synthesis logs for corpora with altered prosodic words? All ASFs are placed in @artic/Experiments/pros...
- 11:37 Task #3806 (Resolved): "mlýneček" sounds like "mlýmeček"
- Percepce místa artikulace závisí na tranzientu druhého formantu (F2). Jako tradiční akustický korelát místa artikulac...
Also available in: Atom