83 commits

Author	SHA1	Message	Date
Jean-Marc Valin	217c40d4ac	dump cleanup, change alignment ... Remove already-disabled silence chopping code and make time alignment the same as lpcnet_demo -features	2023-09-27 12:57:08 -04:00
Jean-Marc Valin	d88dd89358	Add noise augmentation to pitch dumping	2023-09-26 12:12:46 -04:00
Jean-Marc Valin	0100cd95de	Add pitch feature computation	2023-09-26 12:12:46 -04:00
Jean-Marc Valin	178672ed18	Silencing some warnings	2023-06-28 17:16:53 -04:00
Jean-Marc Valin	9f4fc8bbfa	Replacing RNN_ macros with existing OPUS_ ones	2023-06-23 00:02:12 -04:00
Jean-Marc Valin	b64a89feca	Using opus_int16 instead of short in LPCNet code	2023-06-22 18:07:26 -04:00
Jean-Marc Valin	abe817c3fc	Remove pcount that's no longer useful ... We're back to processing 10 ms at a time and have no need for 40-ms "superframes".	2023-06-22 18:07:25 -04:00
Marcus Asteborg	f36685fc97	Remove trailing whitespace in dnn	2023-06-22 13:58:37 -07:00
Jean-Marc Valin	247e6a587c	Remove support for LPCNet quantization	2023-06-22 00:58:24 -04:00
Jean-Marc Valin	2e18f0d160	Using Burg cepstrum for feature prediction	2022-02-04 22:04:23 -05:00
Jean-Marc Valin	227537c994	Avoiding more symbol clashes with Opus	2022-01-25 00:08:27 -05:00
Jean-Marc Valin	60a009b457	Making codebase C90-compliant	2022-01-19 18:10:44 -05:00
Jean-Marc Valin	71a2656768	Fix potential overflow in training data for large signals	2021-10-30 02:40:47 -04:00
Jean-Marc Valin	144b7311bc	Dumping 16-bit linear training data	2021-10-20 23:35:59 -04:00
Jean-Marc Valin	a3ef596822	auto-detect end-to-end models	2021-10-20 23:35:59 -04:00
Jean-Marc Valin	4a7ce81fb3	Re-enabling quantized feature dump	2021-10-04 03:04:36 -04:00
Jean-Marc Valin	8783ef0088	Same as 47, without the sign augmentation	2021-09-01 12:31:30 -04:00
Jean-Marc Valin	2c9b847454	noise tuning, flip sign of speech signal	2021-08-17 18:17:25 -04:00
Jean-Marc Valin	80751bad70	frame-wise features	2021-08-14 02:06:55 -04:00
Jean-Marc Valin	7331e17e92	Don't remove silence from training data	2021-08-04 14:03:44 -04:00
Krishna Subramani	c1532559a2	Adds end-to-end LPC training ... Making LPC computation and prediction differentiable	2021-08-02 19:28:27 -04:00
Jean-Marc Valin	cba0ecd483	Fix warnings about ignoring fread() return value	2021-08-02 19:02:29 -04:00
Jean-Marc Valin	6585843237	Removing the unused features ... Down to 20 features	2021-07-29 03:20:59 -04:00
Jean-Marc Valin	20fea538c2	more reasonable noise ... was increased too much in 713d53e8a	2021-01-17 21:39:42 -05:00
Jean-Marc Valin	40b309d92b	WIP: 8-bit SIMD for GRU B	2021-01-16 02:11:21 -05:00
Marcus Asteborg	9a7f3e4a3d	Open files in binary mode to enable dump_data to work properly on Windows	2020-08-02 20:45:07 -04:00
Jean-Marc Valin	9b8d72ea87	more noise	2019-04-10 21:30:54 -04:00
Jean-Marc Valin	e63292bd56	Split off decoder code	2019-03-17 13:25:43 -04:00
Jean-Marc Valin	8dcccc8934	library encoder...	2019-03-15 13:52:24 -04:00
Jean-Marc Valin	7086dd73dc	WIP: Splitting off the encoder	2019-03-15 02:44:56 -04:00
Jean-Marc Valin	e198d9beef	renaming	2019-03-14 19:16:37 -04:00
Jean-Marc Valin	100ace67bb	cleanup	2019-03-14 19:11:22 -04:00
Jean-Marc Valin	40ceb487c9	Now encoding to a binary bit-stream (64 bytes/packet)	2019-03-14 18:52:59 -04:00
Jean-Marc Valin	23859d74ff	Add bitpacker (untested)	2019-03-14 18:31:26 -04:00
Jean-Marc Valin	accd7a2bd1	getting rid of the vq_mem global	2019-03-14 18:05:19 -04:00
Jean-Marc Valin	7388486c35	Generating samples using quantized cepstrum LPC	2019-03-12 14:41:37 -04:00
Jean-Marc Valin	6b279094aa	decrease resolution of C0 to fit 7 bits, add one bit to mid VQ	2019-03-12 11:56:34 -04:00
Jean-Marc Valin	b5ff531bf0	Optional quantization	2019-03-12 02:31:15 -04:00
Jean-Marc Valin	0077f4b872	add decoder	2019-03-11 23:56:49 -04:00
Jean-Marc Valin	c9b7efd274	dump as ASCII	2019-03-11 18:00:27 -04:00
Jean-Marc Valin	6f8db93929	Add M-best VQ search	2019-03-11 17:06:29 -04:00
Jean-Marc Valin	bfcf94de2a	cleanup	2019-03-11 15:00:12 -04:00
Jean-Marc Valin	5f830b4578	3-bit interpolation	2019-03-11 12:04:36 -04:00
Jean-Marc Valin	fc4f594e25	Better quantization	2019-03-01 16:34:41 -05:00
Jean-Marc Valin	3fc183df55	adjusting quantization bitrate	2019-02-19 00:14:36 -05:00
Jean-Marc Valin	56820f0d10	quantize cepstrum	2019-02-18 20:40:22 -05:00
Jean-Marc Valin	543ee94037	20-bit VQ	2019-02-15 15:13:14 -05:00
Jean-Marc Valin	5be0e59ff0	quantize period but not correlation yet	2019-02-14 17:34:42 -05:00
Jean-Marc Valin	a2d03c2880	more cleaning up	2019-02-01 03:15:42 -05:00
Jean-Marc Valin	8cb54041b0	reindent	2019-02-01 03:04:23 -05:00