git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3528 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

and python wrapper of dec-wrap in pykaldi

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3527 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3520 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: for language-id setup adding an implementation of Shifted Delta Cepstra (SDC) features and corresponding unit tests.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3519 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3518 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3513 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3505 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

* analyze-counts refactored, accepts symbol table to print counts
* nnet-loss.cc - added sanity check to dim in input posteriors



git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3503 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

(trunk/doc) Changing documentation about getting Kaldi. SF recently seems to disallowing the svn URI access, so we suggest the https one

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3497 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3488 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

various changes related to the determinization with phone insertion. This usually gives us another 20%~40% speedup for determinization on our Babel setup.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3482 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3479 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: bugfix, replace sanity check on lattice structure to the very input, where the lattice should be deterministic and epsilon-free


git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3472 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3452 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

Changes to generate-proxy-keywords.cc so that it can print 'kwid weight proxies' to each line, in addition to print out the FST.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3451 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

* nnet-forward.cc - disable GPU memory caching
* cmvn-to-nnet.cc - add variance flooring
* paste-feats.cc - cosmetic change option description
* train_nnet.sh - import cmvn settings from pre-training
* pretrain_dbn.sh - allow generating input transform from a prototype



git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3449 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: Change matrix library from using std::exp to exp/expf, for speed (thanks to tvarog for pointing the issue out); fix to determinize-lattice-pruned-test.cc to work with current code; disallow certain constructors in util/kaldi-table.h that would not work correctly.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3445 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3443 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3441 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

Changes to lattice determinization: 1. changed deque to priority_queue in EpsilonClosure in determinize-lattice-pruned.cc, which should speed up the determinization process substantially; 2. added KALDI_VLOG(2) debug info to lattice-determinize-pruned.cc and lattice-determinize-pruned-parallel.cc

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3439 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3437 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3435 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk : lattice align tools will produce topologically sorted lattices (can be useful for 3rd party lattice conversion scripts)



git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3431 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3429 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: Change to keyword search (e.g. as used in BABEL program) to be more exact, e.g. with regard to time boundaries; make wspecifiers to scp support permissive (,p) option (see changes to docs for explanation); modify lattice-to-nbest to support random generation from lattice; add some nnet code for perturbing egs (no scripts to demonstrate this yet); misc cosmetic changes.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3424 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3423 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

Fix to discriminative training (retroactive thing and nnet-normalize-stddev), seems working, learning rate needs further tuning

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3421 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3420 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3419 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: change to word-align-lattice.cc so that lattice-align-words will output a partial lattice if not all could be aligned.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3418 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3417 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3416 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk,nnet: updating training scripts (now using prototypes, initializing with 'nnet-initialize'; NN training target represented as 'Posterior'), preparing NNs to allow parallel nested networks.



git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3415 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3414 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: small change to ivector-extractor-acc-stats.cc (make it less memory-hungry when forking to open tables)

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3413 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk,nnet:minor changes to nnet components (<AddBias> <Rescale> are trainable, <Copy> adding initialization)



git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3409 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: thanks to jtrmal, Makefile changes to link only needed libraries; some cosmetic fixes.  also (thanks to dsnyder for testing it): removing the use of weight-regression by default in the speaker-id setup since it causes a degradation.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3405 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3404 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk,nnet: committing latest nnet code, preparation for CNNs, a binary tool for initialization (will be used in examples later)



git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3402 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk,cuda: fixing CuMatrix::AddMat(.) to use 2strides; adding CuMatrix::EqualElementMask(.) which produces per-element equality mask (handy for backpropagation through max-pooling)



git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3400 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8