Add detection for repeated audio in capturing.

content/renderer/media/audio_repetition_detector.cc

+// Copyright 2015 The Chromium Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
+
+#include "content/renderer/media/audio_repetition_detector.h"
+
+#include "base/logging.h"
+#include "base/macros.h"
+
+namespace content {
+
+AudioRepetitionDetector::AudioRepetitionDetector(
+    int min_length_ms, size_t max_frames,
+    const std::vector<int>& look_back_times,
+    const RepetitionCallback& repetition_callback)
+    : max_look_back_ms_(0),
+      min_length_ms_(min_length_ms),
+      sample_rate_(0),
+      buffer_size_frames_(0),
+      buffer_end_index_(0),
+      max_frames_(max_frames),
+      repetition_callback_(repetition_callback) {
+  DCHECK(main_thread_checker_.CalledOnValidThread());
+  processing_thread_checker_.DetachFromThread();
+
+  // Build |states_| for the all look back times. Automatically avoid

[Henrik Grunell, 2015/10/28 17:52:01]

Is this part only for sorting and avoiding duplicates? Could you use a set?
(Could take a set in the ctor in that case.) Otherwise, perhaps std::sort and
std::unique?

[minyue, 2015/10/28 19:45:29]

I actually tried to use set at the first place. It is not handy since expect for
C++11, map<int, Object> needs a copy ctor of Object when you do insert(),
map<int, Object*> can solve it but the lifetime of an Object needs to be taken
care of carefully. Then I used this not-so-efficient way of avoiding
duplication, given that there won't be many look back values.

But thank you for mentioning std:unique. I will try to utilize it here.

[Henrik Grunell, 2015/10/30 10:40:16]

I mean std::set<int>& look_back_times as argument. Then order and uniqueness is
guaranteed already.

+  // duplications in |look_back_times| if any.
+  for (auto look_back : look_back_times) {
+    // States are added in the order of their look back times.
+    auto it = states_.begin();
+    for (; it != states_.end(); ++it) {
+      const int it_look_back = (*it)->look_back_ms();
+      if (it_look_back == look_back)
+        return;
+      if (it_look_back < look_back)
+        break;
+    }
+    states_.insert(it, new State(look_back));
+    if (look_back > max_look_back_ms_) {
+      max_look_back_ms_ = look_back;
+    }
+  }
+}
+
+AudioRepetitionDetector::~AudioRepetitionDetector() {
+  DCHECK(main_thread_checker_.CalledOnValidThread());
+}
+
+void AudioRepetitionDetector::Detect(const float* data, size_t num_frames,
+                                     size_t num_channels, int sample_rate) {
+  DCHECK(processing_thread_checker_.CalledOnValidThread());
+  DCHECK(!states_.empty());
+
+  if (num_channels != num_channels_ || sample_rate != sample_rate_)
+    Reset(num_channels, sample_rate);
+
+  // The maximum number of frames |audio_buffer_| can take in is |max_frames_|.
+  // Therefore, input data with larger frames needs be divided into chunks.
+  const size_t chunk_size = max_frames_ * num_channels;
+  while (num_frames > max_frames_) {
+    Detect(data, max_frames_, num_channels, sample_rate);
+    data += chunk_size;
+    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 (State* state : states_) {
+      // Look back position depends on the sample rate. It is rounded down to
+      // the closest integer.
+      const size_t look_back_frames =
+          state->look_back_ms() * sample_rate_ / 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, num_channels));
+          if (HasValidReport(state)) {
+            repetition_callback_.Run(state->look_back_ms());
+            state->set_reported(true);
+          }
+        }
+      } else {
+        state->Reset();
+      }
+    }
+  }
+}
+
+AudioRepetitionDetector::State::State(int look_back_ms)
+    : look_back_ms_(look_back_ms) {
+  Reset();
+}
+
+void AudioRepetitionDetector::State::Increment(bool zero) {
+  if (0 == count_frames_ && zero) {
+    // If a repetition starts with zeros, we enter the all zero mode until
+    // a non zero is found later. The point is that the beginning zeros should
+    // be counted in the length of the repetition as long as the repetition does
+    // not comprise only zeros.
+    all_zero_ = true;
+  }
+  ++count_frames_;
+  if (!zero)
+    all_zero_ = false;
+}
+
+void AudioRepetitionDetector::State::Reset() {
+  count_frames_ = 0;
+  all_zero_ = true;
+  reported_ = false;
+}
+
+void AudioRepetitionDetector::Reset(size_t num_channels, int sample_rate) {
+  DCHECK(processing_thread_checker_.CalledOnValidThread());
+  num_channels_ = num_channels;
+  sample_rate_ = sample_rate;
+
+  // |(xxx + 999) / 1000| is an arithmetic way to round up |xxx / 1000|.
+  buffer_size_frames_ =
+      (max_look_back_ms_ * sample_rate_ + 999) / 1000 + max_frames_;
+
+  audio_buffer_.resize(buffer_size_frames_ * num_channels_);
+  for (State* state : states_)
+    state->Reset();
+}
+
+void AudioRepetitionDetector::AddFramesToBuffer(const float* data,
+                                                size_t num_frames) {
+  DCHECK(processing_thread_checker_.CalledOnValidThread());
+  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 AudioRepetitionDetector::Equal(const float* frame,
+                                    int look_back_frames) const {
+  DCHECK(processing_thread_checker_.CalledOnValidThread());
+  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 channel = 0; channel < num_channels_; ++channel, ++frame, ++it) {
+    if (*frame != *it)
+      return false;
+  }
+  return true;
+}
+
+bool AudioRepetitionDetector::IsZero(const float* frame,
+                                     size_t num_channels) const {
+  for (size_t channel = 0; channel < num_channels; ++channel, ++frame) {
+    if (*frame != 0)
+      return false;
+  }
+  return true;
+}
+
+bool AudioRepetitionDetector::HasValidReport(const State* state) const {
+  return (!state->all_zero() && state->count_frames() >=
+      static_cast<size_t>(min_length_ms_ * sample_rate_ / 1000));
+}
+
+}  // namespace content