summaryrefslogtreecommitdiffstats
path: root/third_party/libwebrtc/modules/audio_coding/neteq/post_decode_vad.cc
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-19 00:47:55 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-19 00:47:55 +0000
commit26a029d407be480d791972afb5975cf62c9360a6 (patch)
treef435a8308119effd964b339f76abb83a57c29483 /third_party/libwebrtc/modules/audio_coding/neteq/post_decode_vad.cc
parentInitial commit. (diff)
downloadfirefox-26a029d407be480d791972afb5975cf62c9360a6.tar.xz
firefox-26a029d407be480d791972afb5975cf62c9360a6.zip
Adding upstream version 124.0.1.upstream/124.0.1
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'third_party/libwebrtc/modules/audio_coding/neteq/post_decode_vad.cc')
-rw-r--r--third_party/libwebrtc/modules/audio_coding/neteq/post_decode_vad.cc90
1 files changed, 90 insertions, 0 deletions
diff --git a/third_party/libwebrtc/modules/audio_coding/neteq/post_decode_vad.cc b/third_party/libwebrtc/modules/audio_coding/neteq/post_decode_vad.cc
new file mode 100644
index 0000000000..9999d6764b
--- /dev/null
+++ b/third_party/libwebrtc/modules/audio_coding/neteq/post_decode_vad.cc
@@ -0,0 +1,90 @@
+/*
+ * Copyright (c) 2013 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 "modules/audio_coding/neteq/post_decode_vad.h"
+
+namespace webrtc {
+
+PostDecodeVad::~PostDecodeVad() {
+ if (vad_instance_)
+ WebRtcVad_Free(vad_instance_);
+}
+
+void PostDecodeVad::Enable() {
+ if (!vad_instance_) {
+ // Create the instance.
+ vad_instance_ = WebRtcVad_Create();
+ if (vad_instance_ == nullptr) {
+ // Failed to create instance.
+ Disable();
+ return;
+ }
+ }
+ Init();
+ enabled_ = true;
+}
+
+void PostDecodeVad::Disable() {
+ enabled_ = false;
+ running_ = false;
+}
+
+void PostDecodeVad::Init() {
+ running_ = false;
+ if (vad_instance_) {
+ WebRtcVad_Init(vad_instance_);
+ WebRtcVad_set_mode(vad_instance_, kVadMode);
+ running_ = true;
+ }
+}
+
+void PostDecodeVad::Update(int16_t* signal,
+ size_t length,
+ AudioDecoder::SpeechType speech_type,
+ bool sid_frame,
+ int fs_hz) {
+ if (!vad_instance_ || !enabled_) {
+ return;
+ }
+
+ if (speech_type == AudioDecoder::kComfortNoise || sid_frame ||
+ fs_hz > 16000) {
+ // TODO(hlundin): Remove restriction on fs_hz.
+ running_ = false;
+ active_speech_ = true;
+ sid_interval_counter_ = 0;
+ } else if (!running_) {
+ ++sid_interval_counter_;
+ }
+
+ if (sid_interval_counter_ >= kVadAutoEnable) {
+ Init();
+ }
+
+ if (length > 0 && running_) {
+ size_t vad_sample_index = 0;
+ active_speech_ = false;
+ // Loop through frame sizes 30, 20, and 10 ms.
+ for (int vad_frame_size_ms = 30; vad_frame_size_ms >= 10;
+ vad_frame_size_ms -= 10) {
+ size_t vad_frame_size_samples =
+ static_cast<size_t>(vad_frame_size_ms * fs_hz / 1000);
+ while (length - vad_sample_index >= vad_frame_size_samples) {
+ int vad_return =
+ WebRtcVad_Process(vad_instance_, fs_hz, &signal[vad_sample_index],
+ vad_frame_size_samples);
+ active_speech_ |= (vad_return == 1);
+ vad_sample_index += vad_frame_size_samples;
+ }
+ }
+ }
+}
+
+} // namespace webrtc