OLD | NEW |
1 /* | 1 /* |
2 * Copyright (c) 2014 The WebRTC project authors. All Rights Reserved. | 2 * Copyright (c) 2014 The WebRTC project authors. All Rights Reserved. |
3 * | 3 * |
4 * Use of this source code is governed by a BSD-style license | 4 * Use of this source code is governed by a BSD-style license |
5 * that can be found in the LICENSE file in the root of the source | 5 * that can be found in the LICENSE file in the root of the source |
6 * tree. An additional intellectual property rights grant can be found | 6 * tree. An additional intellectual property rights grant can be found |
7 * in the file PATENTS. All contributing project authors may | 7 * in the file PATENTS. All contributing project authors may |
8 * be found in the AUTHORS file in the root of the source tree. | 8 * be found in the AUTHORS file in the root of the source tree. |
9 */ | 9 */ |
10 | 10 |
(...skipping 91 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
102 size_t window_size = static_cast<size_t>(1) << RealFourier::FftOrder(freqs_); | 102 size_t window_size = static_cast<size_t>(1) << RealFourier::FftOrder(freqs_); |
103 std::vector<float> kbd_window(window_size); | 103 std::vector<float> kbd_window(window_size); |
104 WindowGenerator::KaiserBesselDerived(kKbdAlpha, window_size, | 104 WindowGenerator::KaiserBesselDerived(kKbdAlpha, window_size, |
105 kbd_window.data()); | 105 kbd_window.data()); |
106 render_mangler_.reset(new LappedTransform( | 106 render_mangler_.reset(new LappedTransform( |
107 num_render_channels_, num_render_channels_, chunk_length_, | 107 num_render_channels_, num_render_channels_, chunk_length_, |
108 kbd_window.data(), window_size, window_size / 2, this)); | 108 kbd_window.data(), window_size, window_size / 2, this)); |
109 } | 109 } |
110 | 110 |
111 void IntelligibilityEnhancer::SetCaptureNoiseEstimate( | 111 void IntelligibilityEnhancer::SetCaptureNoiseEstimate( |
112 std::vector<float> noise) { | 112 std::vector<float> noise, int gain_db) { |
113 RTC_DCHECK_EQ(noise.size(), num_noise_bins_); | 113 RTC_DCHECK_EQ(noise.size(), num_noise_bins_); |
| 114 const float gain = std::pow(10.f, gain_db / 20.f); |
| 115 for (auto& bin : noise) { |
| 116 bin *= gain; |
| 117 } |
114 // Disregarding return value since buffer overflow is acceptable, because it | 118 // Disregarding return value since buffer overflow is acceptable, because it |
115 // is not critical to get each noise estimate. | 119 // is not critical to get each noise estimate. |
116 if (noise_estimation_queue_.Insert(&noise)) { | 120 if (noise_estimation_queue_.Insert(&noise)) { |
117 }; | 121 }; |
118 } | 122 } |
119 | 123 |
120 void IntelligibilityEnhancer::ProcessRenderAudio(float* const* audio, | 124 void IntelligibilityEnhancer::ProcessRenderAudio(float* const* audio, |
121 int sample_rate_hz, | 125 int sample_rate_hz, |
122 size_t num_channels) { | 126 size_t num_channels) { |
123 RTC_CHECK_EQ(sample_rate_hz_, sample_rate_hz); | 127 RTC_CHECK_EQ(sample_rate_hz_, sample_rate_hz); |
(...skipping 214 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
338 vad_.ProcessChunk(audio_s16_.data(), chunk_length_, sample_rate_hz_); | 342 vad_.ProcessChunk(audio_s16_.data(), chunk_length_, sample_rate_hz_); |
339 if (vad_.last_voice_probability() > kVoiceProbabilityThreshold) { | 343 if (vad_.last_voice_probability() > kVoiceProbabilityThreshold) { |
340 chunks_since_voice_ = 0; | 344 chunks_since_voice_ = 0; |
341 } else if (chunks_since_voice_ < kSpeechOffsetDelay) { | 345 } else if (chunks_since_voice_ < kSpeechOffsetDelay) { |
342 ++chunks_since_voice_; | 346 ++chunks_since_voice_; |
343 } | 347 } |
344 return chunks_since_voice_ < kSpeechOffsetDelay; | 348 return chunks_since_voice_ < kSpeechOffsetDelay; |
345 } | 349 } |
346 | 350 |
347 } // namespace webrtc | 351 } // namespace webrtc |
OLD | NEW |