shithub: opus

14fb264a – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2020/06/20 19:47

Fix sampling bug for 16-bit rand()

8f887b62 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/04/13 23:20

Download the model

60790784 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/04/11 07:06

training

9b8d72ea – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/04/10 17:30

more noise

a3300d7b – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/04/10 17:13

Fix bias in LPC spectrum

fd1fc693 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/04/01 11:22

adaptation flag to avoid training the sample rate network

2a7a9fa0 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/28 07:33

Minor README.md tweak again

49fc5f74 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/28 07:29

nothing to see here

63a67d46 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/28 07:23

Add README.md to tarball

ee63653f – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/28 07:19

Update README.md with new paper

1f450815 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/28 06:54

Implement -feature option

77d02dbd – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/27 10:12

Using macros for sizes in the demo

9f78e583 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/27 10:06

Make param ordering consistent for lpcnet_synthesize()

623ac954 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/24 08:10

Adding API doc

219fbff4 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/23 23:48

Making it easier to adapt (or not) a model

edee9cd8 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/22 10:37

README.md update

a8fb25f1 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/20 09:36

Remove NaN checks

a0981592 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/20 08:57

Neon: Make gcc actually generate VMLA instructions for sparse mul

2bc20e65 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/19 23:21

Remove hack to match Python code

492ef9b3 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/19 23:03

Neon implementation of the activation functions

ddd38bd2 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/19 10:50

Merge branch 'autotools1'

3d2b26b7 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/19 10:42

Add dump_data

df8a0ac3 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/19 10:22

build lpcnet_demo in root dir

a9871fe6 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/19 00:08

Add README

30c7545a – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/18 17:54

Fixing Makefile

2c0e9679 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/18 17:53

Fixing dynamic libraries

849f3abf – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/18 17:43

Making autogen.sh download and unpack the model

a0b0ece1 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/18 16:50

Add missing headers

89b2e064 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/18 16:09

Fixes

55a15a93 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/18 16:05

s/rnnoise/lpcnet/ (untested)

f41c9776 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/18 15:57

Copied from RNNoise directly

ba38c160 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/18 13:49

Fix auto-download (even more of a hack)

77eb0061 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/18 13:40

Auto-download data (still a hack)

54bd6208 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/18 12:17

Adding lpcnet_demo

54b057c9 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/18 10:13

Add LPCNet decoder object

fe608dfc – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/18 09:42

Moving LPCNetState

e63292bd – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/17 09:24

Split off decoder code

8dcccc89 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/15 09:52

library encoder...

7086dd73 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/14 22:44

WIP: Splitting off the encoder

e198d9be – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/14 15:16

renaming

100ace67 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/14 15:11

cleanup

40ceb487 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/14 14:52

Now encoding to a binary bit-stream (64 bytes/packet)

23859d74 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/14 14:26

Add bitpacker (untested)

accd7a2b – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/14 14:05

getting rid of the vq_mem global

7cee743c – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/12 10:43

minor update to training code

7388486c – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/12 10:41

Generating samples using quantized cepstrum LPC

6b279094 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/12 07:56

decrease resolution of C0 to fit 7 bits, add one bit to mid VQ

b5ff531b – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/11 22:31

Optional quantization

0077f4b8 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/11 19:56

add decoder

c9b7efd2 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/11 14:00

dump as ASCII

6f8db939 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/11 13:06

Add M-best VQ search

bfcf94de – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/11 11:00

cleanup

5f830b45 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/11 08:04

3-bit interpolation

fc4f594e – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/03/01 11:34

Better quantization

3fc183df – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/02/18 19:14

adjusting quantization bitrate

56820f0d – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/02/18 15:40

quantize cepstrum

29610751 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/02/15 20:37

oops, include DC in difference codebook

90d74bbb – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2019/02/15 13:12

Add bidirectional quantizer

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