• <ins id="pjuwb"></ins>
    <blockquote id="pjuwb"><pre id="pjuwb"></pre></blockquote>
    <noscript id="pjuwb"></noscript>
          <sup id="pjuwb"><pre id="pjuwb"></pre></sup>
            <dd id="pjuwb"></dd>
            <abbr id="pjuwb"></abbr>

            夜貓子

            夜貓子
            隨筆 - 5, 文章 - 1, 評論 - 1, 引用 - 0
            數(shù)據(jù)加載中……

            speex開源庫分析(前置處理)

            1.簡介

            語音在采集和傳輸過程中,由于語音源的差異、信道的衰減、噪聲的干擾以及遠(yuǎn)近效應(yīng),導(dǎo)致信號幅度相差很大。所有在語音處理之前我們需要對語音數(shù)據(jù)進(jìn)行前置處理,包括預(yù)處理(AGCVAD、回音消除)、重采樣和噪聲抑制。

            所有的代碼都是基于speex開源庫,具體內(nèi)容可以參考http://speex.org/

            本開發(fā)手冊暫時(shí)只提供AGC的接口和測試代碼,其他陸續(xù)添加進(jìn)來。

            2.接口說明

            2.1  介紹

            預(yù)處理模塊包括自動(dòng)增益控制、靜音檢測和回音消除。以下是接口函數(shù),具體參考speex\ speex_preprocess.h

             

            函數(shù)名稱

            功能簡介

            speex_preprocess_state_init

            創(chuàng)建預(yù)處理器

            speex_preprocess_state_destroy

            銷毀預(yù)處理器

            speex_preprocess_run

            處理一幀數(shù)據(jù)

            speex_preprocess

            處理一幀數(shù)據(jù)(廢棄的)

            speex_preprocess_estimate_update

            更新預(yù)處理器

            speex_preprocess_ctl

            設(shè)置和讀取預(yù)處理器的參數(shù)

             

            2.1.1  speex_preprocess_state_init

            函數(shù)原形

            SpeexPreprocessState *speex_preprocess_state_init(int frame_size, int sampling_rate);

            功能

            創(chuàng)建預(yù)處理器

            參數(shù)

            Frmae_size   [in]每幀的大小(建議幀長為20ms

            Sample_rate  [in]采樣率(支持8k16k44k

            返回值

            成功返回預(yù)處理器指針,失敗返回NULL

            說明

            加入是16k的語音數(shù)據(jù),幀長20ms等于320個(gè)采樣

             

            2.1.2  speex_preprocess_state_destroy

            函數(shù)原形

            void speex_preprocess_state_destroy(SpeexPreprocessState *st);

            功能

            銷毀預(yù)處理器

            參數(shù)

            St           [in]處理器指針

            返回值

            Void

            說明

             

             

            2.1.3  speex_preprocess_run

            函數(shù)原形

            int speex_preprocess_run(SpeexPreprocessState *st, spx_int16_t *x);

            功能

            處理一幀語音數(shù)據(jù)

            參數(shù)

            St           [in]處理器指針

            X            [in|out]數(shù)據(jù)緩存,處理后的數(shù)據(jù)也存入該緩存中

            返回值

            如果VAD打開,返回值為1表示有語音,為0表示靜音或者噪音

            說明

             

             

            2.1.4  speex_preprocess

            函數(shù)原形

            int speex_preprocess(SpeexPreprocessState *st, spx_int16_t *x, spx_int32_t *echo);

            功能

            處理一幀語音數(shù)據(jù)(廢棄的函數(shù),簡介調(diào)用speex_preprocess_run

            參數(shù)

            St           [in]處理器指針

            X            [in|out]數(shù)據(jù)緩存,處理后的數(shù)據(jù)也存入該緩存中     

            返回值

             

            說明

             

             

            2.1.5  speex_preprocess_estimate_update

            函數(shù)原形

            void speex_preprocess_estimate_update(SpeexPreprocessState *st, spx_int16_t *x);

            功能

            更新預(yù)處理器,不會(huì)計(jì)算輸出語音

            參數(shù)

            St           [in]處理器指針

            X            [in]數(shù)據(jù)緩存

            返回值

            Void

            說明

             

             

            2.1.6  speex_preprocess_ctl

            函數(shù)原形

            int speex_preprocess_ctl(SpeexPreprocessState *st, int request, void *ptr);

            功能

            設(shè)置預(yù)處理器的參數(shù)

            參數(shù)

            St           [in]處理器指針

            Request      [in]參數(shù)的類型(由宏來代表不同的參數(shù))

            Ptr          [in|out]參數(shù)的值(設(shè)置參數(shù)時(shí)為in,獲得參數(shù)參數(shù)時(shí)為out,這個(gè)由宏決定)

            返回值

            成功返回0,失敗返回-1(表明未知的請求參數(shù))

            說明

            以下數(shù)標(biāo)識參數(shù)類型的宏

            /** Set preprocessor denoiser state */

            #define SPEEX_PREPROCESS_SET_DENOISE 0

            /** Get preprocessor denoiser state */

            #define SPEEX_PREPROCESS_GET_DENOISE 1

             

            /** Set preprocessor Automatic Gain Control state */

            #define SPEEX_PREPROCESS_SET_AGC 2

            /** Get preprocessor Automatic Gain Control state */

            #define SPEEX_PREPROCESS_GET_AGC 3

             

            /** Set preprocessor Voice Activity Detection state */

            #define SPEEX_PREPROCESS_SET_VAD 4

            /** Get preprocessor Voice Activity Detection state */

            #define SPEEX_PREPROCESS_GET_VAD 5

             

            /** Set preprocessor Automatic Gain Control level (float) */

            #define SPEEX_PREPROCESS_SET_AGC_LEVEL 6

            /** Get preprocessor Automatic Gain Control level (float) */

            #define SPEEX_PREPROCESS_GET_AGC_LEVEL 7

             

            /** Set preprocessor dereverb state */

            #define SPEEX_PREPROCESS_SET_DEREVERB 8

            /** Get preprocessor dereverb state */

            #define SPEEX_PREPROCESS_GET_DEREVERB 9

             

            /** Set preprocessor dereverb level */

            #define SPEEX_PREPROCESS_SET_DEREVERB_LEVEL 10

            /** Get preprocessor dereverb level */

            #define SPEEX_PREPROCESS_GET_DEREVERB_LEVEL 11

             

            /** Set preprocessor dereverb decay */

            #define SPEEX_PREPROCESS_SET_DEREVERB_DECAY 12

            /** Get preprocessor dereverb decay */

            #define SPEEX_PREPROCESS_GET_DEREVERB_DECAY 13

             

            /** Set probability required for the VAD to go from silence to voice */

            #define SPEEX_PREPROCESS_SET_PROB_START 14

            /** Get probability required for the VAD to go from silence to voice */

            #define SPEEX_PREPROCESS_GET_PROB_START 15

             

            /** Set probability required for the VAD to stay in the voice state (integer percent) */

            #define SPEEX_PREPROCESS_SET_PROB_CONTINUE 16

            /** Get probability required for the VAD to stay in the voice state (integer percent) */

            #define SPEEX_PREPROCESS_GET_PROB_CONTINUE 17

             

            /** Set maximum attenuation of the noise in dB (negative number) */

            #define SPEEX_PREPROCESS_SET_NOISE_SUPPRESS 18

            /** Get maximum attenuation of the noise in dB (negative number) */

            #define SPEEX_PREPROCESS_GET_NOISE_SUPPRESS 19

             

            /** Set maximum attenuation of the residual echo in dB (negative number) */

            #define SPEEX_PREPROCESS_SET_ECHO_SUPPRESS 20

            /** Get maximum attenuation of the residual echo in dB (negative number) */

            #define SPEEX_PREPROCESS_GET_ECHO_SUPPRESS 21

             

            /** Set maximum attenuation of the residual echo in dB when near end is active (negative number) */

            #define SPEEX_PREPROCESS_SET_ECHO_SUPPRESS_ACTIVE 22

            /** Get maximum attenuation of the residual echo in dB when near end is active (negative number) */

            #define SPEEX_PREPROCESS_GET_ECHO_SUPPRESS_ACTIVE 23

             

            /** Set the corresponding echo canceller state so that residual echo suppression can be performed (NULL for no residual echo suppression) */

            #define SPEEX_PREPROCESS_SET_ECHO_STATE 24

            /** Get the corresponding echo canceller state */

            #define SPEEX_PREPROCESS_GET_ECHO_STATE 25

             

            /** Set maximal gain increase in dB/second (int32) */

            #define SPEEX_PREPROCESS_SET_AGC_INCREMENT 26

             

            /** Get maximal gain increase in dB/second (int32) */

            #define SPEEX_PREPROCESS_GET_AGC_INCREMENT 27

             

            /** Set maximal gain decrease in dB/second (int32) */

            #define SPEEX_PREPROCESS_SET_AGC_DECREMENT 28

             

            /** Get maximal gain decrease in dB/second (int32) */

            #define SPEEX_PREPROCESS_GET_AGC_DECREMENT 29

             

            /** Set maximal gain in dB (int32) */

            #define SPEEX_PREPROCESS_SET_AGC_MAX_GAIN 30

             

            /** Get maximal gain in dB (int32) */

            #define SPEEX_PREPROCESS_GET_AGC_MAX_GAIN 31

             

            /*  Can't set loudness */

            /** Get loudness */

            #define SPEEX_PREPROCESS_GET_AGC_LOUDNESS 33

             

            /*  Can't set gain */

            /** Get current gain (int32 percent) */

            #define SPEEX_PREPROCESS_GET_AGC_GAIN 35

             

            /*  Can't set spectrum size */

            /** Get spectrum size for power spectrum (int32) */

            #define SPEEX_PREPROCESS_GET_PSD_SIZE 37

             

            /*  Can't set power spectrum */

            /** Get power spectrum (int32[] of squared values) */

            #define SPEEX_PREPROCESS_GET_PSD 39

             

            /*  Can't set noise size */

            /** Get spectrum size for noise estimate (int32)  */

            #define SPEEX_PREPROCESS_GET_NOISE_PSD_SIZE 41

             

            /*  Can't set noise estimate */

            /** Get noise estimate (int32[] of squared values) */

            #define SPEEX_PREPROCESS_GET_NOISE_PSD 43

             

            /* Can't set speech probability */

            /** Get speech probability in last frame (int32).  */

            #define SPEEX_PREPROCESS_GET_PROB 45

             

            /** Set preprocessor Automatic Gain Control level (int32) */

            #define SPEEX_PREPROCESS_SET_AGC_TARGET 46

            /** Get preprocessor Automatic Gain Control level (int32) */

            #define SPEEX_PREPROCESS_GET_AGC_TARGET 47

             

            3.實(shí)例代碼

            3.1  AGC

            #define NN 320

            /*

                語音數(shù)據(jù)為單通道、16bit16k

            */

            int _tmain(int argc, _TCHAR* argv[])

            {

             

                 short in[NN];

                 int i;

                 SpeexPreprocessState *st;

                 int count=0;

                 float f;

             

                 st = speex_preprocess_state_init(NN, 16000);

                

                 i=1;

                 speex_preprocess_ctl(st, SPEEX_PREPROCESS_SET_AGC, &i);

                 f=16000;

                 speex_preprocess_ctl(st, SPEEX_PREPROCESS_SET_AGC_LEVEL, &f);

             

             

                 while (1)

                 {

                     int vad;

                     fread(in, sizeof(short), NN, stdin);

                     if (feof(stdin))

                          break;

                     vad = speex_preprocess_run(st, in);

                     //fprintf (stderr, "%d\n", vad);

                     fwrite(in, sizeof(short), NN, stdout);

                     count++;

                 }

                 speex_preprocess_state_destroy(st);

             

                 return 0;

            }

             

             


             

            posted on 2012-04-24 18:41 夜貓子 閱讀(8021) 評論(1)  編輯 收藏 引用

            評論

            # re: speex開源庫分析(前置處理)  回復(fù)  更多評論   

            speex-1.2beta3-win32版本的libspeex.lib庫中沒有吧preprocess相關(guān)的一些文件放進(jìn)去,所以
            speex_preprocess_state_init
            speex_preprocess_ctl
            speex_preprocess_run
            speex_preprocess_state_destroy就無法調(diào)用了。

            但是dsp版本的libspeexdsp.lib中有卻有,是Win32的不支持嗎?還是什么原因?
            2012-07-11 17:16 | kobewylb
            精品水蜜桃久久久久久久| 综合久久一区二区三区| 亚洲精品国精品久久99热一| 2022年国产精品久久久久| 久久99久久成人免费播放| 久久久久婷婷| 久久r热这里有精品视频| 亚洲精品无码久久久久| 91精品观看91久久久久久| 2021少妇久久久久久久久久| 精品国产乱码久久久久久浪潮| 久久精品视频网| 久久精品国产亚洲AV久| 久久久久久无码国产精品中文字幕 | 久久亚洲国产精品123区| 国产精品久久免费| 久久亚洲电影| 国内精品久久久久久久影视麻豆| 99久久这里只精品国产免费| 伊人久久亚洲综合影院| 久久免费高清视频| 国内精品伊人久久久久影院对白| 国产精品美女久久福利网站| 国产免费久久精品丫丫| 久久国产成人精品国产成人亚洲| 久久天天躁狠狠躁夜夜躁2O2O| 久久99精品久久久久子伦| 国产精品久久久亚洲| 精品久久久中文字幕人妻| 人妻无码精品久久亚瑟影视| 亚洲国产成人久久精品99| 久久精品国产亚洲一区二区三区| 久久99国产精品一区二区| 久久99国产综合精品| 欧洲人妻丰满av无码久久不卡| 亚洲欧洲中文日韩久久AV乱码| 久久无码AV中文出轨人妻| 久久久99精品一区二区| 久久久久久久亚洲精品| 青青热久久国产久精品 | 久久精品黄AA片一区二区三区|