shithub: opus

543ee940 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/02/15 10:13

20-bit VQ

5be0e59f – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/02/14 12:34

quantize period but not correlation yet

a2d03c28 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/31 22:15

more cleaning up

8cb54041 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/31 22:04

reindent

6ef718c4 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/31 21:59

splitting function

6318467f – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/31 21:44

Removing static variables

e1741e37 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/31 21:36

cleaning up

ba2404a5 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/31 10:53

cleanup

d3ec5575 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/31 10:49

Output unquantized pitch info

785c4b2e – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/31 10:14

tweak frame weighting

b3198a09 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/31 09:55

Add frame weighting, doubling prevention

e6347180 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/30 17:17

add backward pass

3a6bae17 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/30 16:31

Dynamic programming approach (wip)

24595ea2 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/30 09:17

pitch tweaks

823be857 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/29 21:29

comments

a15cc201 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/29 21:25

cleanup

cd2065f7 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/29 21:21

replace pitch features

1d70c61a – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/29 12:53

dump 4 frames at a time

71e6bbb5 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/29 12:36

more refactoring

80dcc3f3 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/29 12:31

put back training code

d5a01822 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/29 12:30

refactoring

43ffd19b – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/29 12:08

pitch quantization

48a8f973 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/29 09:34

remove earlier attempt

6d88dfe3 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/29 09:22

misc improvements

a1ab7c5f – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/29 08:34

new pitch

da456b09 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/24 09:13

fix warning

b2940ed2 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/22 11:55

Use real features at the chunk edges rather than zeros

9fd3e45f – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/21 11:53

Avoid glitch at the beginning

b84a06dd – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/21 11:52

Use a single u-law embedding

dc082d7c – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/18 10:08

Making it easier to change the frame size

38cd5cf0 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/17 18:17

Remove useless (and possibly hurtful) residual connection

4698b283 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/17 12:03

Making dump_lpcnet.py a bit more robust

d1811399 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/09 11:52

Cleanup

a06e9a96 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/01/01 09:40

doc update

ba46bb93 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/29 11:13

Biasing noise std

800a659c – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/29 11:13

Using log approximations

677182fc – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/29 10:41

Making the update and reset gate more sparse

ea02ef7e – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/27 21:52

Computing signals in C

d75a4aec – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/27 20:19

refactoring

293f76ee – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/15 20:15

README update

8bd91766 – David <david@rowetel.com> authored on 2018/12/16 04:31

added concat.sh script

8f8ca9c9 – David <david@rowetel.com> authored on 2018/12/16 04:30

updated README

61194468 – David <david@rowetel.com> authored on 2018/12/16 04:30

added Makefile

470a0a7e – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/14 17:29

Properly delaying the pitch gain

6367aa8a – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/13 13:25

Controlling training offset

088ee4ff – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/13 13:03

Should make dump_data able to handle partial overlap

12f16df6 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/13 12:40

More work on making freq.[ch] more generic

fb3112ad – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/13 10:42

Removing most of the full-overlap assumptions from freq.[ch]

e8c96212 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/13 09:37

Missing #include

06b9bfa8 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/12 06:00

Avoiding an infinite loop

7d9affc3 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/11 11:58

Moving the frame out of lpcnet.c and into test_lpcnet.c

ca4a8d4f – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/11 11:53

More cleanup

242198ea – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/11 11:29

Get rid of the TRAINING macro

590e9ce4 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/11 11:25

Move the common functions from dump_data.c to freq.c

9b581a13 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/11 11:10

Rename denoise.c to dump_data.c, rnnoise.h to freq.h

3cb52ece – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/11 10:37

...

86c15a7a – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/11 08:31

Remove more useless code

4eb2d344 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/11 06:49

Cleanup: Remove useless code (more to come)

37ddc0a8 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/10 21:00

Add -test or -train option

74b98437 – David Rowe <david@rowetel.com> authored and Jean-Marc Valin <jmvalin@jmvalin.ca> committed on 2018/12/10 20:41

Vectorization testing code

03dcb819 – David Rowe <david@rowetel.com> authored and Jean-Marc Valin <jmvalin@jmvalin.ca> committed on 2018/12/10 20:40

Error messages

7dc696b9 – David Rowe <david@rowetel.com> authored and Jean-Marc Valin <jmvalin@jmvalin.ca> committed on 2018/12/10 16:28

refactored for different machines, sgemv_accum16 using NEON intrisics

bc108e9a – David <david@rowetel.com> authored and Jean-Marc Valin <jmvalin@jmvalin.ca> committed on 2018/12/07 06:29

checks that files opened OK

8c271d60 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/10 11:15

Controlling per-gate sparsity

b9e0ea23 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/10 06:23

Fix flooring of the pitch period

d533e402 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/10 06:22

Fix DCT normalization

a02d9c85 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/09 16:21

reduce memory use of training code

2facc08b – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/09 16:20

Avoid rounding the prediction multiple times

3e712482 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/09 11:00

Fix compile

0fb031a9 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/01 10:58

Produce at least ~14 hours of augmented speech

3dcbb012 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/01 10:52

Add variable gain and response

f9337256 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/01 09:38

Chopping silence from the training data

407eec12 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/09 10:45

make dump_data output LPC as converted from features

e0d2b105 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/07 13:16

Compute LPC from features

1dcd5732 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/06 11:27

Do proper saturation

771cc786 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/01 21:10

Support for plain AVX with no FMA

91d90676 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/12/01 07:05

Remove the need for useless exc and pred files

b05f950e – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/30 05:56

Using the right name: s/gemm/sgemv/

c395a68b – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/30 05:46

moving code around

05f4851d – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/30 05:32

Making the code work even without AVX2/FMA

1956467d – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/29 20:55

Add AVX2/FMA to gcc options

d7f0abcd – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/29 15:09

Delaying the softmax() to avoid the pow()

faf3fe3d – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/29 14:50

gemm_accum16() doesn't need a multiple of 16 columns (just lines).

7ee79b63 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/29 14:43

Add AXV versions of exp(), tanh() and sigmoid()

d961d009 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/28 15:20

Managing to actually use sparse matrices

4de3e53a – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/28 13:49

Adding some sparse GRU support

ec671ed9 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/28 09:57

Quick and dirty AVX2 implementation of gemm_accum

15fb1b3c – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/28 09:13

Moving GRU_A's condition computation to the frame rate network

732fce9a – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/28 09:05

Pre-computing GRU_A's input contribution.

040aa437 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/28 07:37

Simper GRU implementation just for reset_after.

6c2f7e58 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/27 10:08

compiling synthesis

36a0bf8c – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/27 09:50

Wow, managed two bugs in a 25-character line

c7b978b9 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/27 09:37

Fix reset_after GRU

3c694db2 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/27 08:11

Better rounding

0ddfdfc7 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/27 07:34

Add deemphasis

5ac0ac7a – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/27 06:43

Add code for copying the LPC

e25a585d – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/26 19:23

Match Python boundary condition

4ccfbdff – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/26 13:41

Frame network seems to be working

538f2556 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/26 11:02

Starting to actually test this -- fix a few OOB reads

8d62ba06 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2018/11/26 10:39

...