Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(734)

Side by Side Diff: webrtc/modules/audio_processing/audio_processing_impl.cc

Issue 1693823004: Use VAD to get a better speech power estimation in the IntelligibilityEnhancer (Closed) Base URL: https://chromium.googlesource.com/external/webrtc.git@pow
Patch Set: Use f for float Created 4 years, 10 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View unified diff | Download patch
« no previous file with comments | « no previous file | webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer.h » ('j') | no next file with comments »
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
OLDNEW
1 /* 1 /*
2 * Copyright (c) 2012 The WebRTC project authors. All Rights Reserved. 2 * Copyright (c) 2012 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 1166 matching lines...) Expand 10 before | Expand all | Expand 10 after
1177 capture_nonlocked_.fwd_proc_format.sample_rate_hz() == 1177 capture_nonlocked_.fwd_proc_format.sample_rate_hz() ==
1178 kSampleRate48kHz) { 1178 kSampleRate48kHz) {
1179 // Something besides public_submodules_->level_estimator is enabled, and we 1179 // Something besides public_submodules_->level_estimator is enabled, and we
1180 // have super-wb. 1180 // have super-wb.
1181 return true; 1181 return true;
1182 } 1182 }
1183 return false; 1183 return false;
1184 } 1184 }
1185 1185
1186 bool AudioProcessingImpl::is_rev_processed() const { 1186 bool AudioProcessingImpl::is_rev_processed() const {
1187 return constants_.intelligibility_enabled && 1187 return constants_.intelligibility_enabled;
1188 public_submodules_->intelligibility_enhancer->active();
1189 } 1188 }
1190 1189
1191 bool AudioProcessingImpl::render_check_rev_conversion_needed() const { 1190 bool AudioProcessingImpl::render_check_rev_conversion_needed() const {
1192 return rev_conversion_needed(); 1191 return rev_conversion_needed();
1193 } 1192 }
1194 1193
1195 bool AudioProcessingImpl::rev_conversion_needed() const { 1194 bool AudioProcessingImpl::rev_conversion_needed() const {
1196 return (formats_.api_format.reverse_input_stream() != 1195 return (formats_.api_format.reverse_input_stream() !=
1197 formats_.api_format.reverse_output_stream()); 1196 formats_.api_format.reverse_output_stream());
1198 } 1197 }
(...skipping 30 matching lines...) Expand all
1229 private_submodules_->beamformer.reset(new NonlinearBeamformer( 1228 private_submodules_->beamformer.reset(new NonlinearBeamformer(
1230 capture_.array_geometry, capture_.target_direction)); 1229 capture_.array_geometry, capture_.target_direction));
1231 } 1230 }
1232 private_submodules_->beamformer->Initialize(kChunkSizeMs, 1231 private_submodules_->beamformer->Initialize(kChunkSizeMs,
1233 capture_nonlocked_.split_rate); 1232 capture_nonlocked_.split_rate);
1234 } 1233 }
1235 } 1234 }
1236 1235
1237 void AudioProcessingImpl::InitializeIntelligibility() { 1236 void AudioProcessingImpl::InitializeIntelligibility() {
1238 if (constants_.intelligibility_enabled) { 1237 if (constants_.intelligibility_enabled) {
1239 IntelligibilityEnhancer::Config config;
1240 config.sample_rate_hz = capture_nonlocked_.split_rate;
1241 config.num_capture_channels = capture_.capture_audio->num_channels();
1242 config.num_render_channels = render_.render_audio->num_channels();
1243 public_submodules_->intelligibility_enhancer.reset( 1238 public_submodules_->intelligibility_enhancer.reset(
1244 new IntelligibilityEnhancer(config)); 1239 new IntelligibilityEnhancer(capture_nonlocked_.split_rate,
1240 render_.render_audio->num_channels()));
1245 } 1241 }
1246 } 1242 }
1247 1243
1248 void AudioProcessingImpl::InitializeHighPassFilter() { 1244 void AudioProcessingImpl::InitializeHighPassFilter() {
1249 public_submodules_->high_pass_filter->Initialize(num_proc_channels(), 1245 public_submodules_->high_pass_filter->Initialize(num_proc_channels(),
1250 proc_sample_rate_hz()); 1246 proc_sample_rate_hz());
1251 } 1247 }
1252 1248
1253 void AudioProcessingImpl::InitializeNoiseSuppression() { 1249 void AudioProcessingImpl::InitializeNoiseSuppression() {
1254 public_submodules_->noise_suppression->Initialize(num_proc_channels(), 1250 public_submodules_->noise_suppression->Initialize(num_proc_channels(),
(...skipping 201 matching lines...) Expand 10 before | Expand all | Expand 10 after
1456 debug_dump_.capture.event_msg->mutable_config()->CopyFrom(config); 1452 debug_dump_.capture.event_msg->mutable_config()->CopyFrom(config);
1457 1453
1458 RETURN_ON_ERR(WriteMessageToDebugFile(debug_dump_.debug_file.get(), 1454 RETURN_ON_ERR(WriteMessageToDebugFile(debug_dump_.debug_file.get(),
1459 &debug_dump_.num_bytes_left_for_log_, 1455 &debug_dump_.num_bytes_left_for_log_,
1460 &crit_debug_, &debug_dump_.capture)); 1456 &crit_debug_, &debug_dump_.capture));
1461 return kNoError; 1457 return kNoError;
1462 } 1458 }
1463 #endif // WEBRTC_AUDIOPROC_DEBUG_DUMP 1459 #endif // WEBRTC_AUDIOPROC_DEBUG_DUMP
1464 1460
1465 } // namespace webrtc 1461 } // namespace webrtc
OLDNEW
« no previous file with comments | « no previous file | webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer.h » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698