-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Added nioTSO's EA MicroTalk encoder to the project
- Loading branch information
Tony Bark
committed
May 7, 2024
1 parent
4bee18c
commit 41be518
Showing
14 changed files
with
2,374 additions
and
4 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,49 @@ | ||
## EA MicroTalk | ||
|
||
EA MicroTalk (also UTalk or UTK) is a linear-predictive speech codec used in | ||
various games by Electronic Arts. The earliest known game to use it is | ||
Beasts & Bumpkins (1997). The codec has a bandwidth of 11.025kHz (sampling rate | ||
22.05kHz) and frame size of 20ms (432 samples) and only supports mono. It is | ||
typically encoded at 32 kbit/s. | ||
|
||
Docs: http://wiki.niotso.org/UTK | ||
|
||
In this repository, I have created a set of open source (public domain | ||
via the UNLICENSE) MicroTalk decoders/encoders. | ||
|
||
* Use utkdecode to decode Maxis UTK (The Sims Online, SimCity 4). | ||
* Use utkdecode-bnb to decode PT/M10 (Beasts & Bumpkins). | ||
* Use utkdecode-fifa to decode FIFA 2001/2002 (PS2) speech samples. This tool | ||
supports regular MicroTalk and MicroTalk Revision 3 | ||
[SCxl files](https://wiki.multimedia.cx/index.php/Electronic_Arts_SCxl).(*) | ||
* Use utkencode to encode Maxis UTK. (This is the simplest container format and | ||
is currently the only one supported for encoding.) | ||
|
||
(*) I wasn't able to find any real-world MicroTalk Rev. 3 samples in any games. | ||
However, you can transcode a FIFA MicroTalk Rev. 2 file to Rev. 3 using | ||
[EA's Sound eXchange tool](https://wiki.multimedia.cx/index.php/Electronic_Arts_Sound_eXchange) | ||
(`sx -mt_blk input.dat -=output.dat`). | ||
|
||
## Compiling | ||
|
||
``` | ||
gcc -Wall -Wextra -Wno-unused-function -ansi -pedantic -O2 -ffast-math -fwhole-program -g0 -s -static-libgcc -o utkdecode utkdecode.c | ||
gcc -Wall -Wextra -Wno-unused-function -ansi -pedantic -O2 -ffast-math -fwhole-program -g0 -s -static-libgcc -o utkdecode-fifa utkdecode-fifa.c | ||
gcc -Wall -Wextra -Wno-unused-function -ansi -pedantic -O2 -ffast-math -fwhole-program -g0 -s -static-libgcc -o utkdecode-bnb utkdecode-bnb.c | ||
gcc -Wall -Wextra -Wno-unused-function -ansi -pedantic -O2 -ffast-math -fwhole-program -g0 -s -static-libgcc -o utkencode utkencode.c | ||
``` | ||
|
||
## How the encoder works | ||
|
||
The encoder for now is very simple. It does LPC analysis using the Levinson | ||
algorithm and transmits the entire excitation signal explicitly. Compression is | ||
achieved by choosing a large fixed codebook gain, such that each excitation | ||
sample has a large (coarse) quantization step size. Error is minimized in the | ||
excitation domain, and the quality is somewhat poor for bitrates below about | ||
48 kbit/s. | ||
|
||
However, MicroTalk is a multi-pulse codec (it is cheap to code long runs of | ||
zeros in the excitation signal). Hence, a much better design (and indeed the | ||
standard practice for multi-pulse speech codecs) is to search for the positions | ||
and amplitudes of n pulses such that error is minimized in the output domain | ||
(or the perceptually weighted domain). This new encoder is still in the works. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,24 @@ | ||
This is free and unencumbered software released into the public domain. | ||
|
||
Anyone is free to copy, modify, publish, use, compile, sell, or | ||
distribute this software, either in source code form or as a compiled | ||
binary, for any purpose, commercial or non-commercial, and by any | ||
means. | ||
|
||
In jurisdictions that recognize copyright laws, the author or authors | ||
of this software dedicate any and all copyright interest in the | ||
software to the public domain. We make this dedication for the benefit | ||
of the public at large and to the detriment of our heirs and | ||
successors. We intend this dedication to be an overt act of | ||
relinquishment in perpetuity of all present and future rights to this | ||
software under copyright law. | ||
|
||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, | ||
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF | ||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. | ||
IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR | ||
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, | ||
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR | ||
OTHER DEALINGS IN THE SOFTWARE. | ||
|
||
For more information, please refer to <http://unlicense.org/> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,77 @@ | ||
typedef struct EAChunk { | ||
uint32_t type; | ||
uint8_t *start; | ||
uint8_t *ptr; | ||
uint8_t *end; | ||
} EAChunk; | ||
|
||
static void chunk_read_bytes(EAChunk *chunk, uint8_t *dest, size_t size) | ||
{ | ||
size_t bytes_remaining = chunk->end - chunk->ptr; | ||
|
||
if (bytes_remaining < size) { | ||
fprintf(stderr, "error: unexpected end of chunk\n"); | ||
exit(EXIT_FAILURE); | ||
} | ||
|
||
memcpy(dest, chunk->ptr, size); | ||
chunk->ptr += size; | ||
} | ||
|
||
static uint32_t chunk_read_u32(EAChunk *chunk) | ||
{ | ||
uint8_t dest[4]; | ||
chunk_read_bytes(chunk, dest, sizeof(dest)); | ||
return dest[0] | (dest[1] << 8) | (dest[2] << 16) | (dest[3] << 24); | ||
} | ||
|
||
static uint32_t chunk_read_u8(EAChunk *chunk) | ||
{ | ||
uint8_t dest; | ||
chunk_read_bytes(chunk, &dest, sizeof(dest)); | ||
return dest; | ||
} | ||
|
||
static uint32_t chunk_read_var_int(EAChunk *chunk) | ||
{ | ||
uint8_t dest[4]; | ||
uint8_t size = chunk_read_u8(chunk); | ||
|
||
if (size > 4) { | ||
fprintf(stderr, "error: invalid varint size %u\n", (unsigned)size); | ||
exit(EXIT_FAILURE); | ||
} | ||
|
||
chunk_read_bytes(chunk, dest, size); | ||
|
||
/* read a big-endian integer of variable length */ | ||
switch (size) { | ||
case 1: return dest[0]; | ||
case 2: return (dest[0]<<8) | dest[1]; | ||
case 3: return (dest[0]<<16) | (dest[1] << 8) | dest[2]; | ||
case 4: return (dest[0]<<24) | (dest[1] << 16) | (dest[2] << 8) | dest[3]; | ||
default: return 0; | ||
} | ||
} | ||
|
||
static EAChunk *read_chunk(FILE *fp) | ||
{ | ||
uint32_t size; | ||
static EAChunk chunk; | ||
static uint8_t buffer[4096]; | ||
|
||
chunk.type = read_u32(fp); | ||
|
||
size = read_u32(fp); | ||
if (size < 8 || size-8 > sizeof(buffer)) { | ||
fprintf(stderr, "error: invalid chunk size %u\n", (unsigned)size); | ||
exit(EXIT_FAILURE); | ||
} | ||
|
||
size -= 8; | ||
read_bytes(fp, buffer, size); | ||
chunk.start = chunk.ptr = buffer; | ||
chunk.end = buffer+size; | ||
|
||
return &chunk; | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,78 @@ | ||
#include <stdint.h> | ||
#include <stdio.h> | ||
#include <stdlib.h> | ||
#include <string.h> | ||
#include <errno.h> | ||
|
||
static void read_bytes(FILE *fp, uint8_t *dest, size_t size) | ||
{ | ||
size_t bytes_copied; | ||
|
||
if (!size) | ||
return; | ||
|
||
bytes_copied = fread(dest, 1, size, fp); | ||
if (bytes_copied < size) { | ||
if (ferror(fp)) | ||
fprintf(stderr, "error: fread failed: %s\n", strerror(errno)); | ||
else | ||
fprintf(stderr, "error: unexpected end of file\n"); | ||
|
||
exit(EXIT_FAILURE); | ||
} | ||
} | ||
|
||
static uint32_t read_u32(FILE *fp) | ||
{ | ||
uint8_t dest[4]; | ||
read_bytes(fp, dest, sizeof(dest)); | ||
return dest[0] | (dest[1] << 8) | (dest[2] << 16) | (dest[3] << 24); | ||
} | ||
|
||
static uint16_t read_u16(FILE *fp) | ||
{ | ||
uint8_t dest[2]; | ||
read_bytes(fp, dest, sizeof(dest)); | ||
return dest[0] | (dest[1] << 8); | ||
} | ||
|
||
static uint16_t read_u8(FILE *fp) | ||
{ | ||
uint8_t dest; | ||
read_bytes(fp, &dest, sizeof(dest)); | ||
return dest; | ||
} | ||
|
||
static void write_bytes(FILE *fp, const uint8_t *dest, size_t size) | ||
{ | ||
if (!size) | ||
return; | ||
|
||
if (fwrite(dest, 1, size, fp) != size) { | ||
fprintf(stderr, "error: fwrite failed: %s\n", strerror(errno)); | ||
exit(EXIT_FAILURE); | ||
} | ||
} | ||
|
||
static void write_u32(FILE *fp, uint32_t x) | ||
{ | ||
uint8_t dest[4]; | ||
dest[0] = (uint8_t)x; | ||
dest[1] = (uint8_t)(x>>8); | ||
dest[2] = (uint8_t)(x>>16); | ||
dest[3] = (uint8_t)(x>>24); | ||
write_bytes(fp, dest, sizeof(dest)); | ||
} | ||
|
||
static void write_u16(FILE *fp, uint16_t x) | ||
{ | ||
uint8_t dest[2]; | ||
dest[0] = (uint8_t)x; | ||
dest[1] = (uint8_t)(x>>8); | ||
write_bytes(fp, dest, sizeof(dest)); | ||
} | ||
|
||
static void write_u8(FILE *fp, uint8_t x) | ||
{ | ||
write_bytes(fp, &x, sizeof(x)); | ||
} |
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Oops, something went wrong.