OLD | NEW |
1 /* | 1 /* |
2 * Copyright (c) 2015 The WebRTC project authors. All Rights Reserved. | 2 * Copyright (c) 2015 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 13 matching lines...) Expand all Loading... |
24 | 24 |
25 // A Voice Activity Detector (VAD) that combines the voice probability from the | 25 // A Voice Activity Detector (VAD) that combines the voice probability from the |
26 // StandaloneVad and PitchBasedVad to get a more robust estimation. | 26 // StandaloneVad and PitchBasedVad to get a more robust estimation. |
27 class VoiceActivityDetector { | 27 class VoiceActivityDetector { |
28 public: | 28 public: |
29 VoiceActivityDetector(); | 29 VoiceActivityDetector(); |
30 | 30 |
31 // Processes each audio chunk and estimates the voice probability. The maximum | 31 // Processes each audio chunk and estimates the voice probability. The maximum |
32 // supported sample rate is 32kHz. | 32 // supported sample rate is 32kHz. |
33 // TODO(aluebs): Change |length| to size_t. | 33 // TODO(aluebs): Change |length| to size_t. |
34 void ProcessChunk(const int16_t* audio, int length, int sample_rate_hz); | 34 void ProcessChunk(const int16_t* audio, size_t length, int sample_rate_hz); |
35 | 35 |
36 // Returns a vector of voice probabilities for each chunk. It can be empty for | 36 // Returns a vector of voice probabilities for each chunk. It can be empty for |
37 // some chunks, but it catches up afterwards returning multiple values at | 37 // some chunks, but it catches up afterwards returning multiple values at |
38 // once. | 38 // once. |
39 const std::vector<double>& chunkwise_voice_probabilities() const { | 39 const std::vector<double>& chunkwise_voice_probabilities() const { |
40 return chunkwise_voice_probabilities_; | 40 return chunkwise_voice_probabilities_; |
41 } | 41 } |
42 | 42 |
43 // Returns a vector of RMS values for each chunk. It has the same length as | 43 // Returns a vector of RMS values for each chunk. It has the same length as |
44 // chunkwise_voice_probabilities(). | 44 // chunkwise_voice_probabilities(). |
(...skipping 16 matching lines...) Expand all Loading... |
61 rtc::scoped_ptr<StandaloneVad> standalone_vad_; | 61 rtc::scoped_ptr<StandaloneVad> standalone_vad_; |
62 PitchBasedVad pitch_based_vad_; | 62 PitchBasedVad pitch_based_vad_; |
63 | 63 |
64 int16_t resampled_[kLength10Ms]; | 64 int16_t resampled_[kLength10Ms]; |
65 AudioFeatures features_; | 65 AudioFeatures features_; |
66 }; | 66 }; |
67 | 67 |
68 } // namespace webrtc | 68 } // namespace webrtc |
69 | 69 |
70 #endif // WEBRTC_MODULES_AUDIO_PROCESSING_VAD_VOICE_ACTIVITY_DETECTOR_H_ | 70 #endif // WEBRTC_MODULES_AUDIO_PROCESSING_VAD_VOICE_ACTIVITY_DETECTOR_H_ |
OLD | NEW |