Tacotron-2: Location Sensitive Attention vs BahdanauMonotonic Attention
Location Sensitive Attention(step 8500)
BahdanauMonotonic Attention(step 8500)
These plots show that BahdanauMonotonic Attention is better.
What are the advantages of Location Sensitive Attention?
hccho2
All 6 comments
Show us the samples please? By the way, you had better change the mel loss function into MAE and watch the alignment again.
begeekmyfriend
on 24 Feb 2019
The results made by location sensitive attention are a little worse(in my opinion).
- Do not the alignment plot and the results(audio quality) match?
- What are the advantages of Location Sensitive Attention?
hccho2
on 25 Feb 2019
As for Chinese mandarin, the evaluation results sound good for me. Here is my T2 fork and https://github.com/Rayhane-mamah/Tacotron-2/issues/292#issuecomment-444823633 is my samples.
begeekmyfriend
on 25 Feb 2019
Did the synthesized results have any misreading or word missing based on Bahdanau Monotonic Attention compared with Location Sensitive Attention?
begeekmyfriend
on 26 Feb 2019
I can not be sure because I am under training.
The following plot with Location Sensitive Attention shows missing words.
hccho2
on 27 Feb 2019
As for Chinese mandarin, the evaluation results sound good for me. Here is my T2 fork and #292 (comment) is my samples.
which is better?location sensitive attention?
linlinsongyun
on 31 Jul 2019
Related issues
a8568730
路
6Comments
begeekmyfriend
路
6Comments
zhf459
路
12Comments
kwibjo
路
4Comments
pandaGst
路
4Comments
Most helpful comment
As for Chinese mandarin, the evaluation results sound good for me. Here is my T2 fork and https://github.com/Rayhane-mamah/Tacotron-2/issues/292#issuecomment-444823633 is my samples.