Index: webrtc/modules/audio_processing/repetition_detector.cc |
diff --git a/webrtc/modules/audio_processing/repetition_detector.cc b/webrtc/modules/audio_processing/repetition_detector.cc |
new file mode 100644 |
index 0000000000000000000000000000000000000000..1d70fef633a0466f271ac05bfe0531ccf7619805 |
--- /dev/null |
+++ b/webrtc/modules/audio_processing/repetition_detector.cc |
@@ -0,0 +1,174 @@ |
+/* |
+ * 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. |
+ */ |
+ |
+#include "webrtc/modules/audio_processing/repetition_detector.h" |
+ |
+#include <algorithm> |
+ |
+#include "webrtc/base/checks.h" |
+#include "webrtc/base/safe_conversions.h" |
+ |
+namespace webrtc { |
+ |
+namespace { |
+static const RepetitionDetector::Pattern kRepetitionPatterns[] = { |
+ // {id_, look_back_, length_} |
+ {0, 10, 10}, |
+ {1, 100, 10} |
+}; |
+static const size_t kMaxFrames = 480; // 10ms * 48kHz |
+} |
+ |
+RepetitionDetector::State::State(int id, int look_back_ms, int min_length_ms) |
+ : id_(id), |
+ look_back_ms_(look_back_ms), |
+ min_length_ms_(min_length_ms) { |
+ Reset(); |
+} |
+ |
+void RepetitionDetector::State::Increment(bool zero) { |
+ if (0 == count_frames_ && zero) { |
+ all_zero_ = true; |
+ } |
+ ++count_frames_; |
+ if (!zero) { |
+ all_zero_ = false; |
+ } |
+} |
+ |
+bool RepetitionDetector::State::HasValidReport(int sample_rate_hz) const { |
+ return (!all_zero_ && count_frames_ >= |
+ rtc::checked_cast<size_t>(min_length_ms_ * sample_rate_hz / 1000)); |
+} |
+ |
+void RepetitionDetector::State::Reset() { |
+ count_frames_ = 0; |
+ all_zero_ = true; |
+ reported_ = false; |
+} |
+ |
+RepetitionDetector::RepetitionDetector() |
+ : max_look_back_ms_(0), |
+ sample_rate_hz_(0), |
+ buffer_size_frames_(0), |
+ buffer_end_index_(0), |
+ max_frames_(kMaxFrames) { |
+ RegisterRepetitionPatterns(kRepetitionPatterns, |
+ sizeof(kRepetitionPatterns) / sizeof (Pattern)); |
+} |
+ |
+RepetitionDetector::~RepetitionDetector() = default; |
+ |
+void RepetitionDetector::RegisterRepetitionPatterns(const Pattern* patterns, |
+ size_t num_patterns) { |
+ Pattern pattern; |
+ for (size_t idx = 0; idx < num_patterns; idx++) { |
+ pattern = patterns[idx]; |
+ states_.push_back(new State(pattern.id_, pattern.look_back_ms_, |
+ pattern.min_length_ms_)); |
+ if (pattern.look_back_ms_ > max_look_back_ms_) { |
+ max_look_back_ms_ = pattern.look_back_ms_; |
+ } |
+ } |
+} |
+ |
+void RepetitionDetector::Reset(size_t num_channels, int sample_rate_hz) { |
+ num_channels_ = num_channels; |
+ sample_rate_hz_ = sample_rate_hz; |
+ int sample_1k = max_look_back_ms_ * sample_rate_hz_; |
+ // |(sample_1k + 999) / 1000| is an arithmetic way to round up |
+ // |sample_1k / 1000| |
+ buffer_size_frames_ = (sample_1k + 999) / 1000 + max_frames_; |
+ audio_buffer_.resize(buffer_size_frames_ * num_channels_); |
+ for (auto state : states_) { |
+ state->Reset(); |
+ } |
+} |
+ |
+void RepetitionDetector::AddFramesToBuffer(const float* data, |
+ size_t num_frames) { |
+ DCHECK_LE(num_frames, buffer_size_frames_); |
+ const size_t margin = buffer_size_frames_ - buffer_end_index_; |
+ const auto it = audio_buffer_.begin() + buffer_end_index_ * num_channels_; |
+ if (num_frames <= margin) { |
+ std::copy(data, data + num_frames * num_channels_, it); |
+ buffer_end_index_ += num_frames; |
+ } else { |
+ std::copy(data, data + margin * num_channels_, it); |
+ std::copy(data + margin * num_channels_, data + num_frames * num_channels_, |
+ audio_buffer_.begin()); |
+ buffer_end_index_ = num_frames - margin; |
+ } |
+} |
+ |
+bool RepetitionDetector::Equal(const float* frame, |
+ int look_back_frames) const { |
+ const size_t look_back_index = |
+ (buffer_end_index_ + buffer_size_frames_ - look_back_frames) % |
+ buffer_size_frames_; |
+ auto it = audio_buffer_.begin() + look_back_index * num_channels_; |
+ for (size_t cdx = 0; cdx < num_channels_; ++cdx, ++frame, ++it) { |
+ if (*frame != *it) { |
+ return false; |
+ } |
+ } |
+ return true; |
+} |
+ |
+bool RepetitionDetector::IsZero(const float* frame) const { |
+ for (size_t cdx = 0; cdx < num_channels_; ++cdx, ++frame) { |
+ if (*frame != 0) { |
+ return false; |
+ } |
+ } |
+ return true; |
+} |
+ |
+void RepetitionDetector::Detect(const float* data, size_t num_frames, |
+ size_t num_channels, int sample_rate_hz) { |
+ DCHECK_GT(states_.size(), 0ul); |
+ if (num_channels != num_channels_ || sample_rate_hz != sample_rate_hz_) { |
+ Reset(num_channels, sample_rate_hz); |
+ } |
+ |
+ while (num_frames > max_frames_) { |
+ Detect(data, max_frames_, num_channels, sample_rate_hz); |
+ data += max_frames_ * num_channels; |
+ num_frames -= max_frames_; |
+ } |
+ |
+ if (num_frames == 0) |
+ return; |
+ |
+ AddFramesToBuffer(data, num_frames); |
+ |
+ for (size_t idx = num_frames; idx > 0; --idx, data += num_channels) { |
+ for (auto state : states_) { |
+ const size_t look_back_frames = |
+ rtc::CheckedDivExact(state->look_back_ms() * sample_rate_hz_, 1000); |
+ // Equal(data, offset) checks if |data| equals the audio frame located |
+ // |offset| frames from the end of buffer. Now a full frame has been |
+ // inserted to the buffer, and thus |offset| should compensate for it. |
+ if (Equal(data, look_back_frames + idx)) { |
+ if (!state->reported()) { |
+ state->Increment(IsZero(data)); |
+ if (state->HasValidReport(sample_rate_hz)) { |
+ ReportRepetition(state->id()); |
+ state->set_reported(true); |
+ } |
+ } |
+ } else { |
+ state->Reset(); |
+ } |
+ } |
+ } |
+} |
+ |
+} // namespace webrtc |