c67e916185
Splitting audio into utterances before processing
...
Advantages:
* No problems with long silences (PocketSphinx doesn't like them)
* Potential for parallelization
* Potential for improved phone timing accuracy
2016-05-17 16:01:10 +02:00
bbc933a821
Temporarily removed --dialog option
2016-05-17 14:28:18 +02:00
2f31c5aa61
Refactoring
...
* Rewriting Timeline<T> to be sparse, i.e., allow gaps
* Added specialized subclasses BoundedTimeline<T> and ContinuousTimeline<T>
* Timed<T> and TimeRange: has-a, not is-a
* Introducing Timed<void>
2016-05-17 14:28:18 +02:00
9eef09145e
Added getPairs function
2016-05-12 21:44:46 +02:00
baf2423b27
Added time manipulation functions to TimeRange and Timeline
2016-04-19 22:06:20 +02:00
895b942df3
Implemented AudioStreamSegment
2016-04-19 22:04:43 +02:00
ce204c68de
Fixed constness
2016-04-19 21:12:44 +02:00
c14fb1c7b2
Fixed output format for structured logging
2016-04-19 19:30:38 +02:00
8d2d100376
Refactored enum serialization/deserialization
2016-04-17 20:22:16 +02:00
44d18d00f8
Added header file to CMakeLists.txt
...
This makes navigation easier for me. Plus, ReSharper didn't like not knowing the header files.
2016-04-14 22:14:57 +02:00
7ce79f9c08
Replaced Boost.Log with small custom logger
...
Boost.Log is a complex monstrosity and I can't get it to build on OS X.
2016-04-14 09:42:47 +02:00
4941bff739
Replaced strerror_s with (less safe) strerror
...
libc++ (Xcode) doesn't seem to support it.
2016-04-13 10:37:10 +02:00
d8fbd3596b
Fixed UnboundedStream constructor
2016-04-13 10:37:10 +02:00
db6f2e076b
Fixed GCC build
2016-04-12 23:04:16 +02:00
4b8e38970a
Added hanging indent to help output to make it more readable
2016-04-12 21:23:15 +02:00
fd6b3b1e2f
Supporting multiple export formats
...
- Simplified XML export format
- Added TSV and JSON formats
- Using TSV as standard export format
2016-04-12 21:08:23 +02:00
90e1375f1b
Handling zero-length audio files
2016-04-12 20:45:47 +02:00
7bc4e37a1a
Improved error handling and error messages
2016-04-12 18:02:52 +02:00
04c828506d
Simplified code using Timeline<T>
2016-04-09 22:07:25 +02:00
83291aa96c
Implemented class Timeline<T>
2016-04-09 20:56:25 +02:00
2be3751a4f
Renamed TimeSegment to TimeRange
2016-03-28 20:30:55 +02:00
8c1e24e9c8
Implemented voice activity detection
2016-03-16 21:01:44 +01:00
425f47491c
Fixed compiler warnings
2016-03-16 21:01:43 +01:00
a8900f80ec
Removing DC offset from audio
...
Also a bit of refactoring regarding audio processing
2016-03-16 21:01:43 +01:00
af5a6649c1
Implemented logging to log file
2016-03-08 22:59:44 +01:00
35ec1f8a45
Introduced template functions to unify enum<->string conversions
2016-03-08 22:20:40 +01:00
ad9d8e6567
Renamed `audioInput` directory to `audio`
2016-03-08 18:21:17 +01:00
b78e418a8f
Refactored audio streams
...
* All streams are now mono (simplifies reasoning about samples)
* Streams can be cloned
* Streams can be seeked within
2016-03-07 21:28:31 +01:00
419b0ec469
Making sure log is written in case of exception
2016-03-06 20:40:31 +01:00
04ca644cca
Added structured logging
2016-03-03 22:31:16 +01:00
cdffb56613
Redirecting pocketsphinx log to main log
2016-03-03 22:31:16 +01:00
7efea6f56b
Prepared for logging using Boost.Log v2
2016-02-29 21:48:27 +01:00
7a1f446ca3
Using GSL
2016-02-29 20:58:58 +01:00
667edf9485
Improved dialog handling
2016-02-10 21:53:58 +01:00
05ef692706
Added (primitive) option to explicitly supply the dialog
2016-02-09 22:08:11 +01:00
9b10f38bcb
Added missing include
2016-02-02 10:13:07 +01:00
f09155e486
Using raw pointers instead of iterators for string manipulation
...
This avoids an assertion error when I temporarily move 1 past end
2016-02-01 20:47:27 +01:00
75872fe45d
Using -dither to prevent recognition errors in connection with zero silence
2016-02-01 20:26:14 +01:00
0cb0153874
Improved phone-to-mouth mapping
2016-01-31 21:39:49 +01:00
7aa6057b8e
Allowing for long pauses in speech without breaking sync
2016-01-28 21:52:50 +01:00
c425885929
Showing combined progress for entire task
2016-01-28 19:13:40 +01:00
8e7fcc4efe
Implemented two-step phone detection for better accuracy
2016-01-28 14:19:32 +01:00
2bfe671f82
Simplified directory structure to make Visual Studio build work
2016-01-08 16:59:18 +01:00
0f33fcfbd0
Removing zero silence, seems like Sphinx doesn't like it
...
See http://cmusphinx.sourceforge.net/wiki/faq#qwhy_my_accuracy_is_poor
I couldn't reproduce the original problem, but it doesn't seem to hurt, either.
2016-01-08 16:44:03 +01:00
31cb3b195c
Showing progress bar
2016-01-08 10:53:35 +01:00
f14feefeb0
Using #pragma once instead of include guards
...
Just looks cleaner
2016-01-06 21:08:39 +01:00
9e9a432f70
Improved formatting of command-line output
2016-01-06 21:08:39 +01:00
5c0fe24fae
Refactoring: Using camelCase throughout
2016-01-06 20:47:37 +01:00
acd13e2890
Added a number of string-related tools.
2016-01-06 20:47:29 +01:00
3e5d6e3625
Using TCLAP to parse command line
2016-01-06 20:47:27 +01:00
e2840dba3f
Fixed warning
2015-12-21 13:26:56 +01:00
4baab9b207
Fixed Windows build
2015-12-21 13:17:14 +01:00
932803d5ad
Ported platform-dependent code
...
Added code for Windows, OS X, Solaris, BSD, and Linux.
Right now, only the Windows version has been tested.
2015-12-14 20:46:31 +01:00
e4b5b39504
Fixed corner cases
...
Handling silences and last mouth shape
2015-12-03 23:07:15 +01:00
7b282ce50f
Using std::string instead of std::wstring for command-line args
...
Turns out that even if I manage to get Unicode command line args,
there still is no portable way of opening a file from a Unicode path.
2015-12-03 23:07:15 +01:00
27ba3ef357
Generating XML output
2015-12-03 23:07:15 +01:00
2ef99119b0
Generating mouth shapes using simple lookup table
2015-12-01 22:55:53 +01:00
994e2be314
Redirecting PocketSphinx log output
2015-12-01 22:55:53 +01:00
d6f5c2ed1e
Reading sound file name from command line
2015-12-01 22:55:53 +01:00
132adb1083
Improved error handling
...
Plus some refactoring
2015-12-01 22:55:53 +01:00
f2f6f75932
Refactoring
...
- Moved phone recognition code to phone_extraction.cpp
- Introduced type centiseconds
- Code reorganization
2015-12-01 22:55:52 +01:00
713e8b5d7f
Fixed comment
2015-10-31 20:41:17 +01:00
d96bf12c96
Fixed model path; enabled fast mode
2015-10-19 22:03:29 +02:00
3cd82e89f8
Reading WAVE file
2015-10-19 22:03:29 +02:00
641f64022d
Implemented WAVE reading, writing, and conversion
2015-10-19 22:03:20 +02:00
Daniel Wolf
Daniel Wolf