Index: webrtc/modules/audio_processing/vad/voice_activity_detector.h |
diff --git a/webrtc/modules/audio_processing/vad/voice_activity_detector.h b/webrtc/modules/audio_processing/vad/voice_activity_detector.h |
new file mode 100644 |
index 0000000000000000000000000000000000000000..8c3325606c47ffb91c3f79a6443b0b7419593f31 |
--- /dev/null |
+++ b/webrtc/modules/audio_processing/vad/voice_activity_detector.h |
@@ -0,0 +1,64 @@ |
+/* |
Andrew MacDonald
2015/06/15 04:32:25
After all reviewers have LGTM'd, please run git cl
aluebs-webrtc
2015/06/16 01:17:52
Acknowledged.
|
+ * Copyright (c) 2015 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. |
+ */ |
+ |
+#ifndef WEBRTC_MODULES_AUDIO_PROCESSING_VAD_VOICE_ACTIVITY_DETECTOR_H_ |
+#define WEBRTC_MODULES_AUDIO_PROCESSING_VAD_VOICE_ACTIVITY_DETECTOR_H_ |
+ |
+#include <vector> |
+ |
+#include "webrtc/base/scoped_ptr.h" |
+#include "webrtc/common_audio/resampler/include/resampler.h" |
+#include "webrtc/modules/audio_processing/vad/vad_audio_proc.h" |
+#include "webrtc/modules/audio_processing/vad/common.h" |
+#include "webrtc/modules/audio_processing/vad/pitch_based_vad.h" |
+#include "webrtc/modules/audio_processing/vad/standalone_vad.h" |
+ |
+namespace webrtc { |
+ |
+// A Voice Activity Detector (VAD) that combines the voice probability from the |
+// StandaloneVad and PitchBasedVad to get a more robust estimation. |
+class VoiceActivityDetector { |
+ public: |
+ VoiceActivityDetector(); |
+ |
+ // Processes each capture audio chunk and estimates the voice probability. The |
+ // maximum supported sample rate is 32kHz. |
+ void ProcessCaptureAudio(const int16_t* audio, int length); |
Andrew MacDonald
2015/06/15 04:32:25
Perhaps ProcessChunk instead? It doesn't have to b
aluebs-webrtc
2015/06/16 01:17:53
Good point! Done.
|
+ |
+ // Because ISAC has a different chunk length, it returns a zero size vector |
Andrew MacDonald
2015/06/15 04:32:25
This is an implementation detail; you could put it
aluebs-webrtc
2015/06/16 01:17:52
Done.
|
+ // every time there is no new data and then return a few chunk's data at once. |
bloch
2015/06/12 23:34:38
I'm thinking about what we discussed; I think I (p
aluebs-webrtc
2015/06/16 01:17:52
It will not have identical values. As you point ou
|
+ std::vector<double> chunkwise_voice_probabilities() const { |
+ return chunkwise_voice_probabilities_; |
Andrew MacDonald
2015/06/15 04:32:26
Since this is called on every chunk, you don't wan
aluebs-webrtc
2015/06/16 01:17:52
Done.
|
+ } |
+ std::vector<double> chunkwise_rms() const { return chunkwise_rms_; } |
Andrew MacDonald
2015/06/15 04:32:25
As above, return a const reference.
aluebs-webrtc
2015/06/16 01:17:52
Done.
|
+ |
+ // Returns the last voice probability, regardless of the internal |
+ // implementation, although it has a few chunks of delay. |
+ float last_voice_probability() const { return last_voice_probability_; } |
Andrew MacDonald
2015/06/15 04:32:25
Should definitely convert things to float later gi
aluebs-webrtc
2015/06/16 01:17:53
Fixed this inconsistency in this CL, since it make
|
+ |
+ private: |
+ std::vector<double> chunkwise_voice_probabilities_; |
+ std::vector<double> chunkwise_rms_; |
+ |
+ double last_voice_probability_; |
bloch
2015/06/12 23:34:38
I know you're just refactoring old code, but is th
Andrew MacDonald
2015/06/15 04:32:26
Agreed, I'm sure these could be floats. However it
aluebs-webrtc
2015/06/16 01:17:52
Yes, I can do this in a follow up CL. But I change
|
+ |
+ Resampler resampler_; |
+ VadAudioProc audio_processing_; |
+ |
+ rtc::scoped_ptr<StandaloneVad> standalone_vad_; |
+ PitchBasedVad pitch_based_vad_; |
+ |
+ int16_t resampled_[kLength10Ms]; |
+ AudioFeatures features_; |
+}; |
+ |
+} // namespace webrtc |
+ |
+#endif // WEBRTC_MODULES_AUDIO_PROCESSING_VAD_VOICE_ACTIVITY_DETECTOR_H_ |