430 lines
14 KiB
C++
430 lines
14 KiB
C++
|
#include <iostream>
|
|||
|
|
#include "ns/noise_suppressor.h"
|
|||
|
|
#include "common.h"
|
|||
|
|
#include <cmath>
|
|||
|
|
#include "agcm.h"
|
|||
|
|
|
|||
|
|
|
|||
|
|
#define MIX_INPUT_CHANNELS 2
|
|||
|
|
// #define MIX_INPUT_SAMPLES (10 * MIX_INPUT_SAMPLE_RATE/1000)
|
|||
|
|
#define MIX_INPUT_SAMPLES 1440
|
|||
|
|
// #define MIX_INPUT_SAMPLES 1024
|
|||
|
|
#define MIX_INPUT_SAMPLE_RATE 48000
|
|||
|
|
|
|||
|
|
//----------------------------------------------
|
|||
|
|
#define MIN(a, b) ((a) < (b) ? (a) : (b))
|
|||
|
|
#define MAX(a, b) ((a) > (b) ? (a) : (b))
|
|||
|
|
// 最大/小音量（db）
|
|||
|
|
#define MIN_DB (-10)
|
|||
|
|
#define MAX_DB (60)
|
|||
|
|
// 最大/小音量： 0: 静音； 100:最大音量
|
|||
|
|
#define MUTE_VOLUME (0)
|
|||
|
|
#define MAX_VOLUME (100)
|
|||
|
|
|
|||
|
|
static int vol_scaler_init(int *scaler, int mindb, int maxdb);
|
|||
|
|
typedef struct VolumeCtlUnit
|
|||
|
|
{
|
|||
|
|
int scaler[MAX_VOLUME + 1]; // 音量表
|
|||
|
|
int zeroDb; // 0db在scaler中的索引
|
|||
|
|
// 自定义需要调节的音量
|
|||
|
|
int micVolume;
|
|||
|
|
VolumeCtlUnit() {
|
|||
|
|
// 音量控制器初始化
|
|||
|
|
zeroDb = vol_scaler_init(scaler, MIN_DB, MAX_DB);
|
|||
|
|
micVolume = 100;
|
|||
|
|
}
|
|||
|
|
} volume_ctl_unit_t;
|
|||
|
|
static volume_ctl_unit_t kVolCtrlUnit;
|
|||
|
|
|
|||
|
|
static int vol_scaler_init(int *scaler, int mindb, int maxdb)
|
|||
|
|
{
|
|||
|
|
double tabdb[MAX_VOLUME + 1];
|
|||
|
|
double tabf [MAX_VOLUME + 1];
|
|||
|
|
int z, i;
|
|||
|
|
|
|||
|
|
for (i = 0; i < (MAX_VOLUME + 1); i++) {
|
|||
|
|
// (mindb, maxdb)平均分成(MAX_VOLUME + 1)份
|
|||
|
|
tabdb[i] = mindb + (maxdb - mindb) * i / (MAX_VOLUME + 1);
|
|||
|
|
// dB = 20 * log(A1 / A2)，当A1，A2相等时，db为0
|
|||
|
|
// 这里以(1 << 14)作为原始声音振幅，得到调节后的振幅(A1),将A1存入音量表中
|
|||
|
|
tabf [i] = pow(10.0, tabdb[i] / 20.0);
|
|||
|
|
scaler[i] = (int)((1 << 14) * tabf[i]); // Q14 fix point
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
z = -mindb * (MAX_VOLUME + 1) / (maxdb - mindb);
|
|||
|
|
z = MAX(z, 0 );
|
|||
|
|
z = MIN(z, MAX_VOLUME);
|
|||
|
|
scaler[0] = 0; // 音量表中，0标识静音
|
|||
|
|
scaler[z] = (1 << 14);// (mindb, maxdb)的中间值作为0db，即不做增益处理
|
|||
|
|
|
|||
|
|
return z;
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
static void vol_scaler_run(int16_t *buf, int n, int volume)
|
|||
|
|
{
|
|||
|
|
/* 简易版
|
|||
|
|
while (n--) {
|
|||
|
|
*buf = (*buf) * multiplier / 100.0;
|
|||
|
|
*buf = std::max((int)*buf, -0x7fff);
|
|||
|
|
*buf = std::min((int)*buf, 0x7fff);
|
|||
|
|
buf++;
|
|||
|
|
}
|
|||
|
|
*/
|
|||
|
|
int multiplier = kVolCtrlUnit.scaler[volume];
|
|||
|
|
if (multiplier > (1 << 14)) {
|
|||
|
|
int32_t v;
|
|||
|
|
while (n--) {
|
|||
|
|
v = ((int32_t)*buf * multiplier) >> 14;
|
|||
|
|
v = MAX(v,-0x7fff);
|
|||
|
|
v = MIN(v, 0x7fff);
|
|||
|
|
*buf++ = (int16_t)v;
|
|||
|
|
}
|
|||
|
|
} else if (multiplier < (1 << 14)) {
|
|||
|
|
while (n--) {
|
|||
|
|
*buf = ((int32_t)*buf * multiplier) >> 14;
|
|||
|
|
buf++;
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
//----------------------------------------------
|
|||
|
|
|
|||
|
|
|
|||
|
|
// usb声卡设备句柄
|
|||
|
|
static rkStreamPtr usbCaptureDev = nullptr;
|
|||
|
|
static SampleInfo kPcmSampleInfo;
|
|||
|
|
|
|||
|
|
// 降噪
|
|||
|
|
using namespace webrtc;
|
|||
|
|
struct audio_buf_t
|
|||
|
|
{
|
|||
|
|
uint8_t* data;
|
|||
|
|
int index;
|
|||
|
|
int size;
|
|||
|
|
};
|
|||
|
|
|
|||
|
|
int main(int argc, char *argv[])
|
|||
|
|
{
|
|||
|
|
if (argc < 1) {
|
|||
|
|
printf("usage: %s rtmp_url \n", argv[0]);
|
|||
|
|
return 0;
|
|||
|
|
}
|
|||
|
|
std::string url = argv[1];
|
|||
|
|
|
|||
|
|
// PCM参数
|
|||
|
|
kPcmSampleInfo.channels = MIX_INPUT_CHANNELS;
|
|||
|
|
kPcmSampleInfo.fmt = SAMPLE_FMT_S16;
|
|||
|
|
kPcmSampleInfo.sample_rate = MIX_INPUT_SAMPLE_RATE;
|
|||
|
|
kPcmSampleInfo.nb_samples = MIX_INPUT_SAMPLES;
|
|||
|
|
|
|||
|
|
// 声卡设备初始化
|
|||
|
|
RkStreamInit(2, capture, kPcmSampleInfo, usbCaptureDev);
|
|||
|
|
|
|||
|
|
// 采集buffer
|
|||
|
|
int ret = 0;
|
|||
|
|
std::shared_ptr<easymedia::SampleBuffer> capData = nullptr;
|
|||
|
|
int buffer_size = GetSampleSize(kPcmSampleInfo) * kPcmSampleInfo.nb_samples;
|
|||
|
|
void *ptr = malloc(buffer_size);
|
|||
|
|
capData = std::make_shared<easymedia::SampleBuffer>(easymedia::MediaBuffer(ptr, buffer_size, -1, ptr, free_memory),
|
|||
|
|
kPcmSampleInfo);
|
|||
|
|
assert(capData);
|
|||
|
|
|
|||
|
|
uint8_t *lineBuffer = nullptr;
|
|||
|
|
size_t lineSize = buffer_size;
|
|||
|
|
lineBuffer = (uint8_t*)malloc(lineSize);
|
|||
|
|
assert(lineBuffer);
|
|||
|
|
|
|||
|
|
// 初始化 FFmpeg
|
|||
|
|
AVFormatContext *oc = NULL;
|
|||
|
|
AVOutputFormat *fmt = NULL;
|
|||
|
|
AVStream *audio_st = NULL;
|
|||
|
|
AVCodecContext *c = NULL;
|
|||
|
|
AVCodecParameters *codec_par = nullptr;
|
|||
|
|
AVCodec *codec = NULL;
|
|||
|
|
|
|||
|
|
avformat_alloc_output_context2(&oc, NULL, "flv", url.c_str()); // RTMP 使用 FLV 封装格式
|
|||
|
|
if (!oc) {
|
|||
|
|
fprintf(stderr, "Could not create output context\n");
|
|||
|
|
return -1;
|
|||
|
|
}
|
|||
|
|
fmt = oc->oformat;
|
|||
|
|
|
|||
|
|
// 创建音频流
|
|||
|
|
audio_st = avformat_new_stream(oc, NULL);
|
|||
|
|
if (!audio_st) {
|
|||
|
|
fprintf(stderr, "Could not create audio stream\n");
|
|||
|
|
return -1;
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
codec_par = audio_st->codecpar;
|
|||
|
|
codec_par->codec_id = AV_CODEC_ID_AAC;
|
|||
|
|
codec_par->codec_type = AVMEDIA_TYPE_AUDIO;
|
|||
|
|
codec_par->codec_tag = 0;
|
|||
|
|
codec_par->bit_rate = 128 * 1024;
|
|||
|
|
codec_par->sample_rate = MIX_INPUT_SAMPLE_RATE;
|
|||
|
|
codec_par->channel_layout = av_get_default_channel_layout(MIX_INPUT_CHANNELS);
|
|||
|
|
codec_par->channels = MIX_INPUT_CHANNELS;
|
|||
|
|
codec_par->format = AV_SAMPLE_FMT_FLTP;
|
|||
|
|
|
|||
|
|
codec = avcodec_find_encoder(AV_CODEC_ID_AAC);
|
|||
|
|
if (!codec) {
|
|||
|
|
fprintf(stderr, "Could not find encoder\n");
|
|||
|
|
return -1;
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
c = avcodec_alloc_context3(codec);
|
|||
|
|
if (avcodec_parameters_to_context(c, codec_par) < 0) {
|
|||
|
|
fprintf(stderr, "avcodec_parameters_to_context failed.\n");
|
|||
|
|
return -1;
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// 打开编码器
|
|||
|
|
if (avcodec_open2(c, codec, NULL) < 0) {
|
|||
|
|
fprintf(stderr, "Could not open encoder\n");
|
|||
|
|
return -1;
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// 写入头信息
|
|||
|
|
av_dump_format(oc, 0, url.c_str(), 1);
|
|||
|
|
|
|||
|
|
if (!(fmt->flags & AVFMT_NOFILE)) {
|
|||
|
|
if (avio_open(&oc->pb, url.c_str(), AVIO_FLAG_WRITE) < 0) {
|
|||
|
|
fprintf(stderr, "Could not open '%s'\n", url.c_str());
|
|||
|
|
return -1;
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// 写入流头信息
|
|||
|
|
if (avformat_write_header(oc, NULL) < 0) {
|
|||
|
|
fprintf(stderr, "Error occurred when opening output URL\n");
|
|||
|
|
return -1;
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
AVFrame *frame = av_frame_alloc();
|
|||
|
|
frame->format = c->sample_fmt;
|
|||
|
|
frame->channel_layout = c->channel_layout;
|
|||
|
|
frame->sample_rate = c->sample_rate;
|
|||
|
|
frame->nb_samples = c->frame_size;
|
|||
|
|
|
|||
|
|
// 分配音频帧缓冲区
|
|||
|
|
int output_bz = av_samples_get_buffer_size(NULL, c->channels, c->frame_size, c->sample_fmt, 0);
|
|||
|
|
uint8_t *samples_data = (uint8_t *)av_malloc(output_bz);
|
|||
|
|
avcodec_fill_audio_frame(frame, c->channels, c->sample_fmt, samples_data, output_bz, 0);
|
|||
|
|
|
|||
|
|
printf("cap_bz = %d, frame_bz=%d, chn=%d, frame_size=%d, fmt=%d\n", buffer_size, output_bz, c->channels, c->frame_size, c->sample_fmt);
|
|||
|
|
|
|||
|
|
// 重采样
|
|||
|
|
uint64_t output_channel_layout = av_get_default_channel_layout(c->channels);
|
|||
|
|
SwrContext *swrCtx = swr_alloc_set_opts(nullptr,
|
|||
|
|
output_channel_layout,
|
|||
|
|
c->sample_fmt,
|
|||
|
|
c->sample_rate,
|
|||
|
|
av_get_default_channel_layout(MIX_INPUT_CHANNELS),
|
|||
|
|
AV_SAMPLE_FMT_S16,
|
|||
|
|
MIX_INPUT_SAMPLE_RATE,
|
|||
|
|
0, nullptr);
|
|||
|
|
if (!swrCtx) {
|
|||
|
|
printf("swr_alloc_set_opts failed.\n");
|
|||
|
|
return 0;
|
|||
|
|
}
|
|||
|
|
if (swr_init(swrCtx) < 0) {
|
|||
|
|
printf("swr_init failed.\n");
|
|||
|
|
return 0;
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// 降噪初始化
|
|||
|
|
AudioBuffer audio(MIX_INPUT_SAMPLE_RATE, MIX_INPUT_CHANNELS,
|
|||
|
|
MIX_INPUT_SAMPLE_RATE, MIX_INPUT_CHANNELS,
|
|||
|
|
MIX_INPUT_SAMPLE_RATE, MIX_INPUT_CHANNELS);
|
|||
|
|
StreamConfig stream_config(MIX_INPUT_SAMPLE_RATE, MIX_INPUT_CHANNELS);
|
|||
|
|
NsConfig cfg;
|
|||
|
|
cfg.target_level = NsConfig::SuppressionLevel::k12dB;
|
|||
|
|
NoiseSuppressor ns(cfg, MIX_INPUT_SAMPLE_RATE, MIX_INPUT_CHANNELS);
|
|||
|
|
bool split_bands = MIX_INPUT_SAMPLE_RATE > 16000;
|
|||
|
|
|
|||
|
|
std::vector<audio_buf_t> cap_in_list;
|
|||
|
|
std::vector<audio_buf_t> ns_out_list;
|
|||
|
|
printf("ns config: %d\n", stream_config.num_samples());
|
|||
|
|
|
|||
|
|
// 推流循环
|
|||
|
|
uint64_t pts = 0;
|
|||
|
|
// FILE *swr_fp = fopen("/root/swr_out.pcm", "wb");
|
|||
|
|
FILE *input_fp = fopen("/root/input_out.pcm", "wb");
|
|||
|
|
while(true)
|
|||
|
|
{
|
|||
|
|
// 采集
|
|||
|
|
size_t read_size = usbCaptureDev->Read(capData->GetPtr(), capData->GetSampleSize(), kPcmSampleInfo.nb_samples);
|
|||
|
|
if (!read_size && errno != EAGAIN) {
|
|||
|
|
printf("capture error: %s\n", strerror(errno));
|
|||
|
|
msleep(10);
|
|||
|
|
continue ;
|
|||
|
|
}
|
|||
|
|
capData->SetSamples(read_size);
|
|||
|
|
|
|||
|
|
// 分流
|
|||
|
|
uint8_t *ptr = (uint8_t*)capData->GetPtr();
|
|||
|
|
for (int i = 0; i < capData->GetSamples(); i++) {
|
|||
|
|
int size = capData->GetSampleSize() / capData->GetSampleInfo().channels;
|
|||
|
|
// 左声道 (2.4G)
|
|||
|
|
// memcpy(wirelessBuffer + i * 2 * size, ptr + i * 2 * size, size);
|
|||
|
|
// memcpy(wirelessBuffer + (i * 2 + 1) * size, ptr + i * 2 * size, size);
|
|||
|
|
// 右声道 (LINE IN)
|
|||
|
|
memcpy(lineBuffer + i * 2 * size, ptr + (i * 2 + 1) * size, size);
|
|||
|
|
memcpy(lineBuffer + (i * 2 + 1) * size, ptr + (i * 2 + 1) * size, size);
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
vol_scaler_run((int16_t *)lineBuffer, capData->GetSamples() * kPcmSampleInfo.channels, kVolCtrlUnit.micVolume);
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
// 降噪处理
|
|||
|
|
#if 1
|
|||
|
|
uint8_t *cap_in = (uint8_t *)malloc(lineSize);
|
|||
|
|
memcpy(cap_in, lineBuffer, lineSize);
|
|||
|
|
audio_buf_t cap_in_buf;
|
|||
|
|
cap_in_buf.data = cap_in;
|
|||
|
|
cap_in_buf.index = 0;
|
|||
|
|
cap_in_buf.size = lineSize;
|
|||
|
|
cap_in_list.emplace_back(cap_in_buf);
|
|||
|
|
int frames = capData->GetSamples();
|
|||
|
|
int frameSize = stream_config.num_samples() * sizeof(int16_t);
|
|||
|
|
while (frames > 0)
|
|||
|
|
{
|
|||
|
|
auto capBuf = cap_in_list.begin();
|
|||
|
|
int readSize = (capBuf->size - capBuf->index) >= frameSize ? frameSize : (capBuf->size - capBuf->index);
|
|||
|
|
|
|||
|
|
uint8_t *data = (uint8_t *)malloc(readSize);
|
|||
|
|
memcpy(data, capBuf->data + capBuf->index, readSize);
|
|||
|
|
|
|||
|
|
// 降噪
|
|||
|
|
{
|
|||
|
|
short *buffer = (short *)data;
|
|||
|
|
audio.CopyFrom(buffer, stream_config);
|
|||
|
|
if (split_bands)
|
|||
|
|
audio.SplitIntoFrequencyBands();
|
|||
|
|
ns.Analyze(audio);
|
|||
|
|
ns.Process(&audio);
|
|||
|
|
if (split_bands)
|
|||
|
|
audio.MergeFrequencyBands();
|
|||
|
|
audio.CopyTo(stream_config, buffer);
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// 存储降噪后的音频
|
|||
|
|
audio_buf_t out;
|
|||
|
|
out.data = data;
|
|||
|
|
out.index = 0;
|
|||
|
|
out.size = readSize;
|
|||
|
|
ns_out_list.emplace_back(out);
|
|||
|
|
// 更新index
|
|||
|
|
frames -= stream_config.num_samples();
|
|||
|
|
capBuf->index += readSize;
|
|||
|
|
// 释放音频资源
|
|||
|
|
if (capBuf->index >= capBuf->size) {
|
|||
|
|
free(capBuf->data);
|
|||
|
|
cap_in_list.erase(cap_in_list.begin());
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
if (ns_out_list.size() <= 2) {
|
|||
|
|
continue;
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
frames = c->frame_size;
|
|||
|
|
while (frames > 0) {
|
|||
|
|
auto nsData = ns_out_list.begin();
|
|||
|
|
|
|||
|
|
int needSize = frames * sizeof(int16_t);
|
|||
|
|
int readSize = (nsData->size - nsData->index) >= needSize ? needSize : (nsData->size - nsData->index);
|
|||
|
|
|
|||
|
|
memcpy(lineBuffer + (c->frame_size - frames)*sizeof(int16_t), nsData->data + nsData->index, readSize);
|
|||
|
|
|
|||
|
|
frames -= readSize/sizeof(int16_t);
|
|||
|
|
nsData->index += readSize;
|
|||
|
|
|
|||
|
|
if (nsData->index >= nsData->size) {
|
|||
|
|
free(nsData->data);
|
|||
|
|
ns_out_list.erase(ns_out_list.begin());
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
#endif
|
|||
|
|
|
|||
|
|
if (input_fp) fwrite(lineBuffer, 1, lineSize, input_fp);
|
|||
|
|
|
|||
|
|
// 重采样
|
|||
|
|
{
|
|||
|
|
const uint8_t** in = (const uint8_t**)&lineBuffer;
|
|||
|
|
uint8_t **out = frame->data;
|
|||
|
|
|
|||
|
|
int len2, out_data_size;
|
|||
|
|
|
|||
|
|
len2 = swr_convert(swrCtx, out, frame->nb_samples, in, capData->GetSamples());
|
|||
|
|
if (len2 < 0) {
|
|||
|
|
printf("swr_convert failed. \n");
|
|||
|
|
break;
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
out_data_size = len2 * c->channels * av_get_bytes_per_sample(c->sample_fmt);
|
|||
|
|
|
|||
|
|
// if (swr_fp) fwrite(frame->data[0], 1, out_data_size, swr_fp);
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// 设置帧时间戳
|
|||
|
|
// frame->pts = av_rescale_q(audio_st->cur_dts, audio_st->time_base, c->time_base);
|
|||
|
|
pts += c->frame_size * 1000 / MIX_INPUT_SAMPLE_RATE;
|
|||
|
|
frame->pts = pts;
|
|||
|
|
|
|||
|
|
// printf("frame pts=%lld, cur_dts=%lld stream_tb=(%d/%d), ctx_tb(%d/%d)\n", frame->pts, audio_st->cur_dts,
|
|||
|
|
// audio_st->time_base.num, audio_st->time_base.den,c->time_base.num, c->time_base.den);
|
|||
|
|
|
|||
|
|
// 发送帧到编码器
|
|||
|
|
ret = avcodec_send_frame(c, frame);
|
|||
|
|
if (ret < 0) {
|
|||
|
|
fprintf(stderr, "Error sending a frame for encoding\n");
|
|||
|
|
break;
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// 接收编码后的数据包
|
|||
|
|
AVPacket pkt;
|
|||
|
|
av_init_packet(&pkt);
|
|||
|
|
pkt.data = NULL;
|
|||
|
|
pkt.size = 0;
|
|||
|
|
|
|||
|
|
while (ret >= 0) {
|
|||
|
|
ret = avcodec_receive_packet(c, &pkt);
|
|||
|
|
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) {
|
|||
|
|
break;
|
|||
|
|
} else if (ret < 0) {
|
|||
|
|
fprintf(stderr, "Error during encoding\n");
|
|||
|
|
break;
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// 将数据包时间戳从编码器时间基转换到流时间基
|
|||
|
|
pkt.stream_index = audio_st->index;
|
|||
|
|
av_packet_rescale_ts(&pkt, c->time_base, audio_st->time_base);
|
|||
|
|
pkt.duration = av_rescale_q(pkt.duration, c->time_base, audio_st->time_base);
|
|||
|
|
|
|||
|
|
// 写入数据包到输出媒体文件
|
|||
|
|
ret = av_interleaved_write_frame(oc, &pkt);
|
|||
|
|
if (ret < 0) {
|
|||
|
|
fprintf(stderr, "Error while writing audio frame\n");
|
|||
|
|
break;
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// 释放数据包
|
|||
|
|
av_packet_unref(&pkt);
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
if (swrCtx)
|
|||
|
|
swr_free(&swrCtx);
|
|||
|
|
if (c)
|
|||
|
|
avcodec_close(c);
|
|||
|
|
if (oc) {
|
|||
|
|
avio_close(oc->pb);
|
|||
|
|
avformat_free_context(oc);
|
|||
|
|
}
|
|||
|
|
if (frame) {
|
|||
|
|
av_frame_free(&frame);
|
|||
|
|
}
|
|||
|
|
if (lineBuffer)
|
|||
|
|
av_free(lineBuffer);
|
|||
|
|
return 0;
|
|||
|
|
}
|