From 5a3f6780c871e8738670b45ea7f77c7a4866f539 Mon Sep 17 00:00:00 2001
From: Jameson Wright <a.jameson.wright@gmail.com>
Date: Mon, 17 Jan 2022 09:03:03 -0500
Subject: [PATCH] FEAT(client): Industry standard for hold time

As request in #2453, this commit implements the industry standard
for microphone hold time for voice activation detection. The calculation
that yields hold time (s) from the iVoiceHold setting is described and
comments are added to describe the function of related fields.

Implements #2453.
---
 src/mumble/AudioInput.cpp | 1 +
 src/mumble/AudioInput.h   | 6 +++++-
 src/mumble/Settings.cpp   | 8 +++++---
 3 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/src/mumble/AudioInput.cpp b/src/mumble/AudioInput.cpp
index 1e42e24f8..70da11b2d 100644
--- a/src/mumble/AudioInput.cpp
+++ b/src/mumble/AudioInput.cpp
@@ -1068,6 +1068,7 @@ void AudioInput::encodeAudioFrame(AudioChunk chunk) {
 	if (!bIsSpeech) {
 		iHoldFrames++;
 		if (iHoldFrames < Global::get().s.iVoiceHold)
+			// Hold mic open until iVoiceHold threshold is reached
 			bIsSpeech = true;
 	} else {
 		iHoldFrames = 0;
diff --git a/src/mumble/AudioInput.h b/src/mumble/AudioInput.h
index c4021433e..3f1225e24 100644
--- a/src/mumble/AudioInput.h
+++ b/src/mumble/AudioInput.h
@@ -210,8 +210,12 @@ protected:
 
 	bool bEchoMulti;
 	Settings::NoiseCancel noiseCancel;
+	// Standard microphone sample rate (samples/s)
 	static const unsigned int iSampleRate = SAMPLE_RATE;
-	static const int iFrameSize           = SAMPLE_RATE / 100;
+	/// Based the sample rate, 48,000 samples/s = 48 samples/ms.
+	/// For each 10 ms, this yields 480 samples. This corresponds numerically with the calculation:
+	/// iFrameSize = 48000 / 100 = 480 samples, allowing a consistent 10ms of audio data per frame.
+	static const int iFrameSize = SAMPLE_RATE / 100;
 
 	QMutex qmSpeex;
 	SpeexPreprocessState *sppPreprocess;
diff --git a/src/mumble/Settings.cpp b/src/mumble/Settings.cpp
index fd617d636..0a7b46db4 100644
--- a/src/mumble/Settings.cpp
+++ b/src/mumble/Settings.cpp
@@ -323,9 +323,11 @@ Settings::Settings() {
 	bOnlyAttenuateSameOutput       = false;
 	bAttenuateLoopbacks            = false;
 	iMinLoudness                   = 1000;
-	iVoiceHold                     = 50;
-	iJitterBufferSize              = 1;
-	iFramesPerPacket               = 2;
+	/// Actual mic hold time is (iVoiceHold / 100) seconds, where iVoiceHold is specified in 'frames',
+	/// each of which is has a size of iFrameSize (see AudioInput.h)
+	iVoiceHold        = 20;
+	iJitterBufferSize = 1;
+	iFramesPerPacket  = 2;
 #ifdef USE_RNNOISE
 	noiseCancelMode = NoiseCancelRNN;
 #else