WebRTC下载要很麻烦,并且学会使用一个库也要花费不少时间,另一方面导入一个第三方库app的体积会加大,因此用了一位大神从WebRTC提出来的模块,但因为是c的所以还要转一次。
WebRTC降噪有两部分代码,一套是定点算法(noise_suppression_x.h),一套是浮点算法(noise_suppression.h)。相对来说浮点算法精度更高,但是耗系统资源更多,特别是浮点计算能力较弱的低端ARM CPU上。
音频处理的时候webrtc一次仅能处理10ms数据,小于10ms的数据不要传入,如果是传入小于10ms的数据最后传入也是按照10ms的数据传出,此时会出现问题。另外支持采样率也只有8K,16K,32K三种,不论是降噪模块,或者是回声消除增益等等均是如此。对于8000采样率,16bit的音频数据,10ms的时间采样点就是80个,一个采样点16bit也就是两个字节,那么需要传入WebRtcNsx_Process的数据就是160字节。对于8000和16000采样率的音频数据在使用时可以不管高频部分,只需要传入低频数据即可,但是对于32K采样率的数据就必须通过滤波接口将数据分为高频和低频传入,传入降噪后再组合成音频数据。大于32K的音频文件就必须要通过重采样接口降频到对应的采样率再处理。
部分代码
- (void)viewDidLoad {
[super viewDidLoad];
NSString *inpath = @"/Users/apple/Desktop/a.wav";
NSString *outpath = @"/Users/apple/Desktop/b.wav";
const char *in_file = [inpath UTF8String];
const char *out_file = [outpath UTF8String];
char in_f[1024];
//把从src地址开始且含有'\0'结束符的字符串复制到以dest开始的地址空间,返回值的类型为char*
strcpy(in_f,in_file);
char out_f[1024];
strcpy(out_f,out_file);
[self noise_suppression:in_f and:out_f];
}
- (void)noise_suppression:(char *)in_file and:(char *)out_file {
//音频采样率
uint32_t sampleRate = 0;
//总音频采样数
uint64_t inSampleCount = 0;
int16_t *inBuffer = [self wavRead_int16:in_file :&sampleRate :&inSampleCount];
//如果加载成功
if (inBuffer != nullptr) {
double startTime = now();
[self nsProcess:inBuffer :sampleRate :(int)inSampleCount :kModerate];
double time_interval = calcElapsed(startTime, now());
printf("time interval: %d ms\n ", (int) (time_interval * 1000));
[self wavWrite_int16:out_file :inBuffer :sampleRate :inSampleCount];
free(inBuffer);
}
}
//写wav文件
- (void)wavWrite_int16:(char *)filename :(int16_t *)buffer :(size_t)sampleRate :(size_t)totalSampleCount {
drwav_data_format format = {};
format.container = drwav_container_riff; // <-- drwav_container_riff = normal WAV files, drwav_container_w64 = Sony Wave64.
format.format = DR_WAVE_FORMAT_PCM; // <-- Any of the DR_WAVE_FORMAT_* codes.
format.channels = 1;
format.sampleRate = (drwav_uint32)sampleRate;
format.bitsPerSample = 16;
drwav *pWav = drwav_open_file_write(filename, &format);
if (pWav) {
drwav_uint64 samplesWritten = drwav_write(pWav, totalSampleCount, buffer);
drwav_uninit(pWav);
if (samplesWritten != totalSampleCount) {
fprintf(stderr, "ERROR\n");
exit(1);
}
}
}
//读取wav文件
- (int16_t *)wavRead_int16:(char *)filename :(uint32_t *)sampleRate :(uint64_t *)totalSampleCount{
unsigned int channels;
int16_t *buffer = drwav_open_and_read_file_s16(filename, &channels, sampleRate, totalSampleCount);
if (buffer == nullptr) {
printf("ERROR.");
}
return buffer;
}
-(int)nsProcess:(int16_t *)buffer :(uint32_t)sampleRate :(int)samplesCount :(enum nsLevel)level {
if (buffer == nullptr) return -1;
if (samplesCount == 0) return -1;
size_t samples = MIN(160, sampleRate / 100);
if (samples == 0) return -1;
uint32_t num_bands = 1;
int16_t *input = buffer;
size_t nTotal = (samplesCount / samples);
NsHandle *nsHandle = WebRtcNs_Create();
int status = WebRtcNs_Init(nsHandle, sampleRate);
if (status != 0) {
printf("WebRtcNs_Init fail\n");
return -1;
}
status = WebRtcNs_set_policy(nsHandle, level);
if (status != 0) {
printf("WebRtcNs_set_policy fail\n");
return -1;
}
for (int i = 0; i < nTotal; i++) {
int16_t *nsIn[1] = {input}; //ns input[band][data]
int16_t *nsOut[1] = {input}; //ns output[band][data]
WebRtcNs_Analyze(nsHandle, nsIn[0]);
WebRtcNs_Process(nsHandle, (const int16_t *const *) nsIn, num_bands, nsOut);
input += samples;
}
WebRtcNs_Free(nsHandle);
return 1;
}