本质上是如何正确地将增益应用于音频样本?
我正在FreeBSD和OSS上进行编程,但是在音频样本中操纵音量对于其他OS和应用程序可能是相同的。
我正在研究其他人的应用程序内部,例如ecasound(在C ++中)和SoX(在C中),但我不知道在读取示例并将其应用于增益时出了什么问题:它变得失真且嘈杂。 我的意思是要理解为什么调低音量不起作用(增益小于1)。
我正在处理立体声16位LE样本。在不施加增益的情况下,它可以完美地工作(记录和播放)。
我以为我应该将整数样本转换为float;乘以增益因子并将其恢复为整数。但这是行不通的。对于函数SoX in src/vol.c中的static int flow
,似乎是完全相同的方法。
下面是我的代码(不使用其他库)。功能回放是我要应用增益的地方。
#include <stdio.h>
#include <unistd.h>
#include <fcntl.h>
#include "/usr/include/sys/soundcard.h"
#include <sys/ioctl.h>
#include <sys/time.h>
#include <sys/stat.h> //man 2 chmod
#include <signal.h>
#define DEBUG 1
#define log(msg) if (DEBUG) printf("[LOG] %s\n",msg)
#define err(msg) {printf("[ERR] %s\n",msg); exit(1); }
const char *device = "/dev/dsp3.1"; //Audio device
char *rawFile = "/tmp/raw-file.wav"; //Raw file to record and playback
int fragmentSize = 256;
int b_continue = 1;
void signalHandler(int sigNum){
log("Signal captured");
b_continue = 0;
}
void configDevice(int fdDsp){
int ossCapabilities = 0;
if(fdDsp == -1)
err("can't open device");
if( ioctl(fdDsp, SNDCTL_DSP_GETCAPS, &ossCapabilities) == -1)
err("unsupported: SNDCTL_DSP_GETCAPS");
/*
* http://www.opensound.com/pguide/audio2.html
*/
if(ossCapabilities & DSP_CAP_TRIGGER != DSP_CAP_TRIGGER){
err("Triggering of recording/playback is not possible with this OSS device.");
}
if(ossCapabilities & DSP_CAP_REALTIME != DSP_CAP_REALTIME){
err("No DSP_CAP_REALTIME.");
}
if(ioctl(fdDsp, SNDCTL_DSP_SETDUPLEX, &ossCapabilities) == -1)
err("can't SNDCTL_DSP_SETDUPLEX");
if(ossCapabilities & DSP_CAP_DUPLEX != DSP_CAP_DUPLEX)
err("can't DSP_CAP_DUPLEX");
int format = AFMT_S16_LE; //set format
if(ioctl(fdDsp, SNDCTL_DSP_SETFMT, &format ) == -1){
err("Error setting format.");
}
int channels = 1; //mono=0 stereo=1
if(ioctl(fdDsp, SNDCTL_DSP_STEREO, &channels ) == -1){
err("Error setting channels." );
}
// FREQUENCY RATE
int speed = 44100;
if(ioctl(fdDsp, SNDCTL_DSP_SPEED, &speed ) == -1){
err("Error setting speed.");
}
// FRAGMENT SIZE
if(ioctl(fdDsp, SNDCTL_DSP_SETBLKSIZE, &fragmentSize) == -1){ //normalmente 2048 bits
err("Cannot SNDCTL_DSP_SETBLKSIZE.");
}
}
void record(){
int fdDsp = open(device, O_RDONLY);
configDevice(fdDsp);
//create file for writing
const int fdOutput = open(rawFile, O_WRONLY | O_CREAT, S_IWUSR | S_IRUSR);
if(fdOutput ==-1)
err("can't open file to write");
log("Recording...");
do{
// Triggers recording
int enableBits = PCM_ENABLE_INPUT;
if(ioctl(fdDsp, SNDCTL_DSP_SETTRIGGER, &enableBits) == -1)
err("Can't record: SNDCTL_DSP_SETTRIGGER");
int *buf[fragmentSize];
read(fdDsp, buf, fragmentSize);
write(fdOutput, buf, fragmentSize);
} while(b_continue == 1);
close(fdOutput);
close(fdDsp);
}
void playback(){
log("Opening file:");
log(rawFile);
log("On device:");
log(device);
int fdDsp = open(device, O_WRONLY);
configDevice(fdDsp);
const int fdInput = open(rawFile, O_RDONLY);
if(fdInput ==-1)
err("can't open file");
log("Playing...");
int eof = 0;
do{
// TRIGGERs PLAYBACK
int enableBits = PCM_ENABLE_OUTPUT;
if(ioctl(fdDsp, SNDCTL_DSP_SETTRIGGER, &enableBits) == -1){
err("Cannot SNDCTL_DSP_SETTRIGGER.");
}
int buf[fragmentSize];
eof = read(fdInput, buf, fragmentSize); //bytes read or -1 if EOF
// audio processing:
for(int i=0;i<fragmentSize;i++){
// learning how to get left and right channels from buffer
int l = (buf)[i] & 0xffff;
int r = ((buf)[i] >> 16) & 0xffff ;
// FIXME: it is causing distortion:
float fl = l;
float fr = r;
fl *= 1.0;
fr *= 0.3; //if different than 1, sounds distorted and noisy
l = fl;
r = fr;
// OK: unite Left and Right channels again
int lr = (l ) | (r << 16);
// OK: other options to mix these two channels:
int lleft = l; //Just the left channel
int rright = (r << 16); //Just the right channel
int lmono = (l << 16) | l; //Left ch. on both channels
int rmono = (r << 16) | r; //Right ch. on both channels
// the output:
(buf)[i] = lr;
}
write(fdDsp, buf, fragmentSize);
if(b_continue == 0) break;
} while(eof > 0);
close(fdInput);
close(fdDsp);
}
int main(int argc, char *argv[])
{
signal(SIGINT, signalHandler);
log("Ctrl^C to stop recording/playback");
record();
b_continue = 1; playback();
log("Stopped.");
return 0;
}
UPDATE:
如CL所指出,我使用了错误的类型,并且read()/ write()的最后一个参数大于缓冲区的大小。
因此,在FreeBSD中,我将缓冲区类型更改为#include <stdint.h>
中定义的int16_t(短)。
现在,我可以根据需要正确应用增益:
float fl = l;
float fr = r;
fl *= 1.0f;
fr *= 1.5f;
l = fl;
r = fr;
我接受CL's答案。
现在音频处理循环每次处理一个样本(左右交错)。
更新的代码:
#include <stdio.h>
#include <unistd.h>
#include <fcntl.h>
#include "/usr/include/sys/soundcard.h"
#include <sys/ioctl.h>
#include <sys/time.h>
#include <sys/stat.h> //man 2 chmod
#include <signal.h>
#include <stdint.h> //has type int16_t (short)
#define DEBUG 1
#define log(msg) if (DEBUG) printf("[LOG] %s\n",msg)
#define err(msg) {printf("[ERR] %s\n",msg); exit(1); }
const char *device = "/dev/dsp3.1"; //Audio device
char *rawFile = "/tmp/stereo.wav"; //Raw file to record and playback
int fragmentSize = 256;
int b_continue = 1;
void signalHandler(int sigNum){
log("Signal captured");
b_continue = 0;
}
void configDevice(int fdDsp){
int ossCapabilities = 0;
if(fdDsp == -1)
err("can't open device");
if( ioctl(fdDsp, SNDCTL_DSP_GETCAPS, &ossCapabilities) == -1)
err("unsupported: SNDCTL_DSP_GETCAPS");
/*
* http://www.opensound.com/pguide/audio2.html
*/
if(ossCapabilities & DSP_CAP_TRIGGER != DSP_CAP_TRIGGER){
err("Triggering of recording/playback is not possible with this OSS device.");
}
if(ossCapabilities & DSP_CAP_REALTIME != DSP_CAP_REALTIME){
err("No DSP_CAP_REALTIME.");
}
if(ioctl(fdDsp, SNDCTL_DSP_SETDUPLEX, &ossCapabilities) == -1)
err("can't SNDCTL_DSP_SETDUPLEX");
if(ossCapabilities & DSP_CAP_DUPLEX != DSP_CAP_DUPLEX)
err("can't DSP_CAP_DUPLEX");
int format = AFMT_S16_LE; //set format
if(ioctl(fdDsp, SNDCTL_DSP_SETFMT, &format ) == -1){
err("Error setting format.");
}
int channels = 1; //mono=0 stereo=1
if(ioctl(fdDsp, SNDCTL_DSP_STEREO, &channels ) == -1){
err("Error setting channels." );
}
// FREQUENCY RATE
int speed = 44100;
if(ioctl(fdDsp, SNDCTL_DSP_SPEED, &speed ) == -1){
err("Error setting speed.");
}
// FRAGMENT SIZE
if(ioctl(fdDsp, SNDCTL_DSP_SETBLKSIZE, &fragmentSize) == -1){ //normalmente 2048 bits
err("Cannot SNDCTL_DSP_SETBLKSIZE.");
}
}
void record(){
int fdDsp = open(device, O_RDONLY);
configDevice(fdDsp);
//create file for writing
const int fdOutput = open(rawFile, O_WRONLY | O_CREAT, S_IWUSR | S_IRUSR);
if(fdOutput ==-1)
err("can't open file to write");
log("Recording...");
do{
// Triggers recording
int enableBits = PCM_ENABLE_INPUT;
if(ioctl(fdDsp, SNDCTL_DSP_SETTRIGGER, &enableBits) == -1)
err("Can't record: SNDCTL_DSP_SETTRIGGER");
// Wrong:
// int *buf[fragmentSize];
// read(fdDsp, buf, fragmentSize);
// write(fdOutput, buf, fragmentSize);
int16_t *buf[fragmentSize/sizeof (int16_t)];
read(fdDsp, buf, fragmentSize/sizeof (int16_t));
write(fdOutput, buf, fragmentSize/sizeof (int16_t));
} while(b_continue == 1);
close(fdOutput);
close(fdDsp);
}
void playback(){
log("Opening file:");
log(rawFile);
log("On device:");
log(device);
int fdDsp = open(device, O_WRONLY);
configDevice(fdDsp);
const int fdInput = open(rawFile, O_RDONLY);
if(fdInput ==-1)
err("can't open file");
log("Playing...");
int eof = 0;
do{
// TRIGGERs PLAYBACK
int enableBits = PCM_ENABLE_OUTPUT;
if(ioctl(fdDsp, SNDCTL_DSP_SETTRIGGER, &enableBits) == -1){
err("Cannot SNDCTL_DSP_SETTRIGGER.");
}
//Wrong buffer type (too large) and wrong last parameter for read():
// int buf[fragmentSize];
// eof = read(fdInput, buf, fragmentSize);
int16_t buf[fragmentSize/sizeof (int16_t)];
eof = read(fdInput, buf, fragmentSize/sizeof (int16_t));
// audio processing:
for(int i=0;i<fragmentSize/sizeof (int16_t);i++){
int16_t l = buf[i];
int16_t r = buf[i+1];
// Using int16_t (short) buffer, gain works but stereo is inverted with factor >= 1.4f
float fl = l;
float fr = r;
fl *= 2.0f;
fr *= 3.0f;
l = fl;
r = fr;
// the output:
(buf)[i] = l;
i++;
(buf)[i] = r;
}
// write(fdDsp, buf, fragmentSize); //wrong
write(fdDsp, buf, fragmentSize/sizeof (int16_t));
if(b_continue == 0) break;
} while(eof > 0);
close(fdInput);
close(fdDsp);
}
int main(int argc, char *argv[])
{
signal(SIGINT, signalHandler);
log("Ctrl^C to stop recording/playback");
record();
b_continue = 1; playback();
log("Stopped.");
return 0;
}
谢谢,
read()/ write()的最后一个参数是字节数,但是buf []中的一项具有多个字节。
在二进制数的二进制补码表示中,负值是(或必须是)符号扩展的,即,最高有效位是1。在此代码中,对于负样本,提取L / R通道或对其进行组合均无法正常工作。
处理负样本的最简单方法是每个样本使用一个数组条目,即short int
。