Skip to content

refactor(vad): store duration constants in ms instead of hops #1200

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
msluszniak merged 1 commit into from
May 29, 2026
Merged

refactor(vad): store duration constants in ms instead of hops #1200

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions ...s/react-native-executorch/common/rnexecutorch/models/voice_activity_detection/Constants.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,9 +21,9 @@ inline constexpr auto kPaddedWindowSize = std::bit_ceil(kWindowSize); // 512
inline constexpr size_t kModelInputMin = 100;
inline constexpr size_t kModelInputMax = 1000;
inline constexpr auto kSpeechThreshold = 0.6f;
inline constexpr size_t kMinSpeechDuration = 25; // 250 ms
inline constexpr size_t kMinSilenceDuration = 10; // 100 ms
inline constexpr size_t kSpeechPad = 3; // 30 ms
inline constexpr size_t kMinSpeechDurationMs = 250;
inline constexpr size_t kMinSilenceDurationMs = 100;
inline constexpr size_t kSpeechPadMs = 30;
inline constexpr size_t kStreamBufferMaxSize = 10 * kSampleRate; // 10s
inline constexpr size_t kStreamBufferMinReserve =
1 * kSampleRate; // 1s of audio
Expand Down
11 changes: 6 additions & 5 deletions ...executorch/common/rnexecutorch/models/voice_activity_detection/VoiceActivityDetection.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -209,7 +209,7 @@ VoiceActivityDetection::postprocess(const std::vector<float> &scores,
if (score >= threshold) {
if (potentialStart == -1) {
potentialStart = i;
} else if (i - potentialStart >= kMinSpeechDuration) {
} else if (i - potentialStart >= kMinSpeechDurationMs / kHopLengthMs) {
triggered = true;
startSegment = potentialStart;
potentialStart = -1;
Expand All @@ -221,7 +221,7 @@ VoiceActivityDetection::postprocess(const std::vector<float> &scores,
if (score < threshold) {
if (potentialEnd == -1) {
potentialEnd = i;
} else if (i - potentialEnd >= kMinSilenceDuration) {
} else if (i - potentialEnd >= kMinSilenceDurationMs / kHopLengthMs) {
triggered = false;
endSegment = potentialEnd;
speechSegments.emplace_back(startSegment, endSegment);
Expand All @@ -237,11 +237,12 @@ VoiceActivityDetection::postprocess(const std::vector<float> &scores,
speechSegments.emplace_back(startSegment, endSegment);
}

constexpr size_t kSpeechPadHops = kSpeechPadMs / kHopLengthMs;
for (auto &[start, end] : speechSegments) {
// std::max(start-kSpeedchPad, 0) might be underflow that is why we use ?
// std::max(start-kSpeechPadHops, 0) might be underflow that is why we use ?
// operator.
start = (start > kSpeechPad ? start - kSpeechPad : 0) * kHopLength;
end = std::min(end + kSpeechPad, scores.size()) * kHopLength;
start = (start > kSpeechPadHops ? start - kSpeechPadHops : 0) * kHopLength;
end = std::min(end + kSpeechPadHops, scores.size()) * kHopLength;
}

// Merge tightly placed segments according to the max allowed gap parameter.
Expand Down
Loading