Daniil

@lspvic Could you please merge this feature to `master` and bump up the library version?

> mm, my suspicion is the network will be ignoring those regions so it won't make a difference. We actually use attention masks (and recently, I am also masking in...

I have contacted Earl Vickers the first author of the paper and he sad that it's not the best algo for rever augmentation. His answer was literally the following: `Sorry,...

As far as I understand the author was referring to the quality of the reverberated signal. He mentioned the absence phase information problem which is described in Section 5 of...

> If you could take examples that have problematic deletions and shift the input by 1 or 2 or 4 frames, and see whether the deletions still appear, that would...

Ok, I look through the code and I believe the `k2.OnlineDenseIntersecter` should do the thing, it has a parameter `num_streams` which as far as I understand should be the number...

I'm working on the Tedlium `conformer_ctc2` recipe.

@csukuangfj @danpovey Do you think it's reasonable to add `warmup` for the decoder module in conformer? In Librispeech `conformer_ctc2` recipe I see that the author added this option in the...

I also can confirm that I have had a successful experience with using Kaldi features for the training dataset and `kaldifeat` with preliminary scaling to [-32768, 32767) for test datsets...

>> I also can confirm that I have had a successful experience with using Kaldi features for the training dataset and kaldifeat with preliminary scaling to [-32768, 32767) for test...