VAD语音活动检测库，linux下编译

/* * Copyright (c) 2012 The WebRTC project authors. All Rights Reserved. * * Use of this source code is governed by a BSD-style license * that can be found in the LICENSE file in the root of the source * tree. An additional intellectual property rights grant can be found * in the file PATENTS. All contributing project authors may * be found in the AUTHORS file in the root of the source tree. */ #include "vad_core.h" #include "signal_processing_library.h" #include "typedefs.h" #include "vad_filterbank.h" #include "vad_gmm.h" #include "vad_sp.h" // Spectrum Weighting static const int16_t kSpectrumWeight[kNumChannels] = { 6, 8, 10, 12, 14, 16 }; static const int16_t kNoiseUpdateConst = 655; // Q15 static const int16_t kSpeechUpdateConst = 6554; // Q15 static const int16_t kBackEta = 154; // Q8 // Minimum difference between the two models, Q5 static const int16_t kMinimumDifference[kNumChannels] = { 544, 544, 576, 576, 576, 576 }; // Upper limit of mean value for speech model, Q7 static const int16_t kMaximumSpeech[kNumChannels] = { 11392, 11392, 11520, 11520, 11520, 11520 }; // Minimum value for mean value static const int16_t kMinimumMean[kNumGaussians] = { 640, 768 }; // Upper limit of mean value for noise model, Q7 static const int16_t kMaximumNoise[kNumChannels] = { 9216, 9088, 8960, 8832, 8704, 8576 }; // Start values for the Gaussian models, Q7 // Weights for the two Gaussians for the six channels (noise) static const int16_t kNoiseDataWeights[kTableSize] = { 34, 62, 72, 66, 53, 25, 94, 66, 56, 62, 75, 103 }; // Weights for the two Gaussians for the six channels (speech) static const int16_t kSpeechDataWeights[kTableSize] = { 48, 82, 45, 87, 50, 47, 80, 46, 83, 41, 78, 81 }; // Means for the two Gaussians for the six channels (noise) static const int16_t kNoiseDataMeans[kTableSize] = { 6738, 4892, 7065, 6715, 6771, 3369, 7646, 3863, 7820, 7266, 5020, 4362 }; // Means for the two Gaussians for the six channels (speech) static const int16_t kSpeechDataMeans[kTableSize] = { 8306, 10085, 10078, 11823, 11843, 6309, 9473, 9571, 10879, 7581, 8180, 7483 }; // Stds for the two Gaussians for the six channels (noise) static const int16_t kNoiseDataStds[kTableSize] = { 378, 1064, 493, 582, 688, 593, 474, 697, 475, 688, 421, 455 }; // Stds for the two Gaussians for the six channels (speech) static const int16_t kSpeechDataStds[kTableSize] = { 555, 505, 567, 524, 585, 1231, 509, 828, 492, 1540, 1079, 850 }; // Constants used in GmmProbability(). // // Maximum number of counted speech (VAD = 1) frames in a row. static const int16_t kMaxSpeechFrames = 6; // Minimum standard deviation for both speech and noise. static const int16_t kMinStd = 384; // Constants in WebRtcVad_InitCore(). // Default aggressiveness mode. static const short kDefaultMode = 0; static const int kInitCheck = 42; // Constants used in WebRtcVad_set_mode_core(). // // Thresholds for different frame lengths (10 ms, 20 ms and 30 ms). // // Mode 0, Quality. static const int16_t kOverHangMax1Q[3] = { 8, 4, 3 }; static const int16_t kOverHangMax2Q[3] = { 14, 7, 5 }; static const int16_t kLocalThresholdQ[3] = { 24, 21, 24 }; static const int16_t kGlobalThresholdQ[3] = { 57, 48, 57 }; // Mode 1, Low bitrate. static const int16_t kOverHangMax1LBR[3] = { 8, 4, 3 }; static const int16_t kOverHangMax2LBR[3] = { 14, 7, 5 }; static const int16_t kLocalThresholdLBR[3] = { 37, 32, 37 }; static const int16_t kGlobalThresholdLBR[3] = { 100, 80, 100 }; // Mode 2, Aggressive. static const int16_t kOverHangMax1AGG[3] = { 6, 3, 2 }; static const int16_t kOverHangMax2AGG[3] = { 9, 5, 3 }; static const int16_t kLocalThresholdAGG[3] = { 82, 78, 82 }; static const int16_t kGlobalThresholdAGG[3] = { 285, 260, 285 }; // Mode 3, Very aggressive. static const int16_t kOverHangMax1VAG[3] = { 6, 3, 2 }; static const int16_t kOverHangMax2VAG[3] = { 9, 5, 3 }; static const int16_t kLocalThresholdVAG[3] = { 94, 94, 94 }; static const int16_t kGlobalThresholdVAG[3] = { 1100, 1050, 1100 }; // Calculates the weighted average w.r.t. number of Gaussians. The |data| are // updated with an |offset| before averaging. // // - data [i/o] : Data to average. // - offset [i] : An offset added to |data|. // - weights [i] : Weights used for averaging. // // returns : The weighted average. static int32_t WeightedAverage(int16_t* data, int16_t offset, const int16_t* weights) { int k; int32_t weighted_average = 0; for (k = 0; k < kNumGaussians; k++) { data[k * kNumChannels] += offset; weighted_average += data[k * kNumChannels] * weights[k * kNumChannels]; } return weighted_average; } // Calculates the probabilities for both speech and background noise using // Gaussian Mixture Models (GMM). A hypothesis-test is performed to decide which // type of signal is most probable. // // - self [i/o] : Pointer to VAD instance // - features [i] : Feature vector of length |kNumChannels| // = log10(energy in frequency band) // - total_power [i] : Total power in audio frame. // - frame_length [i] : Number of input samples // // - returns : the VAD decision (0 - noise, 1 - speech). static int16_t GmmProbability(VadInstT* self, int16_t* features, int16_t total_power, int frame_length) { int channel, k; int16_t feature_minimum; int16_t h0, h1; int16_t log_likelihood_ratio; int16_t vadflag = 0; int16_t shifts_h0, shifts_h1; int16_t tmp_s16, tmp1_s16, tmp2_s16; int16_t diff; int gaussian; int16_t nmk, nmk2, nmk3, smk, smk2, nsk, ssk; int16_t delt, ndelt; int16_t maxspe, maxmu; int16_t deltaN[kTableSize], deltaS[kTableSize]; int16_t ngprvec[kTableSize] = { 0 }; // Conditional probability = 0. int16_t sgprvec[kTableSize] = { 0 }; // Conditional probability = 0. int32_t h0_test, h1_test; int32_t tmp1_s32, tmp2_s32; int32_t sum_log_likelihood_ratios = 0; int32_t noise_global_mean, speech_global_mean; int32_t noise_probability[kNumGaussians], speech_probability[kNumGaussians]; int16_t overhead1, overhead2, individualTest, totalTest; // Set various thresholds based on frame lengths (80, 160 or 240 samples). if (frame_length == 80) { overhead1 = self->over_hang_max_1[0]; overhead2 = self->over_hang_max_2[0]; individualTest = self->individual[0]; totalTest = self->total[0]; } else if (frame_length == 160) { overhead1 = self->over_hang_max_1[1]; overhead2 = self->over_hang_max_2[1]; individualTest = self->individual[1]; totalTest = self->total[1]; } else { overhead1 = self->over_hang_max_1[2]; overhead2 = self->over_hang_max_2[2]; individualTest = self->individual[2]; totalTest = self->total[2]; } if (total_power > kMinEnergy) { // The signal power of current frame is large enough for processing. The // processing consists of two parts: // 1) Calculating the likelihood of speech and thereby a VAD decision. // 2) Updating the underlying model, w.r.t., the decision made. // The detection scheme is an LRT with hypothesis // H0: Noise // H1: Speech // // We combine a global LRT with local tests, for each frequency sub-band, // here defined as |channel|. for (channel = 0; channel < kNumChannels; channel++) { // For each channel we model the probability with a GMM consisting of // |kNumGaussians|, with different means and standard deviations depending // on H0 or H1. h0_test = 0; h1_test = 0; for (k = 0; k < kNumGaussians; k++) { gaussian = channel + k * kNumChannels; // Probability under H0, that is, probability of frame being noise. // Value given in Q27 = Q7 * Q20. tmp1_s32 = WebRtcVad_GaussianProbability(features[channel], self->noise_means[gaussian],