Speech without the keyword no longer reaches STT (V-487)

Until now every utterance near the microphone became a turn. SurfaceVoice caps acts at L0, which made that safe rather than expensive, but L0 does not cap reading: the room could still hear his facts read back. The gate sits at dispatch, not at the VAD. The keyword opens a window, the VAD closes the utterance when he stops, and dispatch asks whether the window was open. That ordering is what lets him say "Мэйвен" and then a sentence: the window has to outlive the word by the length of what follows it. One keyword buys one turn. A window that renewed itself on every reply would leave the microphone open for as long as he kept talking, which is the state this exists to end. Her own voice cannot wake her. Every path above the gate returns while the player is running, so no frame of her reply is ever scored, and the streaming state is cleared when playback ends. Nil is a working value. Without -wake-model the gate is open and this is yesterday's mavwaked, which is what an operator with a missing file should get rather than a daemon that refuses to listen. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013ptwopxyo3Z2kwFckHkLvN
2026-08-09 14:19:01 +04:00
parent 877b1fd4f8
commit 479b0c4475
2 changed files with 107 additions and 5 deletions
@@ -12,10 +12,12 @@
 // samples and the capture frame is 480, so silero.go re-chunks. This comment
 // used to say the two matched, which was true of silero v4.
 //
-// There is still no wake-word model, so anything spoken near the microphone
-// becomes a turn (V-487 stage two). The SurfaceVoice auth layer caps all
-// commands at L0 (no destructive acts), which is what makes an accidental
-// trigger safe rather than expensive.
+// The keyword is "Мэйвен" and it is required, when -wake-model points at the
+// head (V-487 stage two). Without it anything spoken near the microphone
+// becomes a turn, which the SurfaceVoice auth layer makes safe rather than
+// expensive: it caps all commands at L0, no destructive acts. It does not cap
+// reading, so an open gate still lets the room hear his facts read back.
+// wakeword.go holds the cadence and wakefeatures.go the three models.
 //
 // The conn carries both directions. mavwaked sends utterances and receives
 // proactive nudges on it, and it is opened at startup rather than at the first
@@ -62,6 +64,12 @@ const (
 	defaultAddr     = "127.0.0.1:9100"
 	defaultLang     = "ru"
 	defaultReadSize = 4096 // max PCM bytes per read from arecord (fits multiple frames)
+
+	// defaultWakeWindowMs — how long the keyword stays good for. He says
+	// "Мэйвен" and then a sentence, and the VAD does not close the utterance
+	// until he stops, so this has to outlive the word by the length of what
+	// follows it. It is spent on dispatch: one keyword, one turn.
+	defaultWakeWindowMs = 8000
 )

 func main() {
@@ -86,6 +94,11 @@ func run(args []string) error {
 	vadModel := flag.String("vad-model", "", "silero-vad onnx file; empty runs the energy threshold instead")
 	vadThreshold := flag.Float64("vad-threshold", defaultSileroThreshold, "speech probability a frame must clear")
 	onnxLib := flag.String("onnx-lib", os.Getenv("MAVEN_ONNX_LIB"), "libonnxruntime.so, needed with -vad-model")
+	wakeModel := flag.String("wake-model", "", "keyword head onnx; empty ships every utterance, as before V-487")
+	wakeMel := flag.String("wake-mel", "", "melspectrogram.onnx, required with -wake-model")
+	wakeEmbed := flag.String("wake-embed", "", "embedding_model.onnx, required with -wake-model")
+	wakeThreshold := flag.Float64("wake-threshold", defaultWakeThreshold, "score the keyword must clear")
+	wakeWindowMs := flag.Int("wake-window-ms", defaultWakeWindowMs, "ms an utterance may still start after the keyword")
 	flag.CommandLine.Parse(args)

 	ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM, syscall.SIGHUP)
@@ -171,6 +184,21 @@ func run(args []string) error {
 	}
 	sess := newSession(vad, newAplayPlayer(), &voiceSender{vc: vc}, *lang, barge)

+	// Keyword gate. A model that will not load is logged and not fatal, for
+	// the same reason silero's is not: an open gate is the daemon he had
+	// yesterday, and a daemon that refuses to start is not.
+	if *wakeModel != "" {
+		w, err := newWakeWord(*wakeMel, *wakeEmbed, *wakeModel, *onnxLib, *wakeThreshold)
+		if err != nil {
+			log.Printf("mavwaked: wake word unavailable, every utterance is a turn: %v", err)
+		} else {
+			defer w.Close()
+			sess.UseWakeWord(w, time.Duration(*wakeWindowMs)*time.Millisecond)
+			log.Printf("mavwaked: wake word from %s, threshold %.3f, window %dms",
+				*wakeModel, *wakeThreshold, *wakeWindowMs)
+		}
+	}
+
 	// Listen for nudges alongside capture. Connect eagerly so mavend has a
 	// voice session before he has said anything: without one, a nudge routed
 	// to voice finds nobody home and goes to the away channels instead.
@@ -20,6 +20,15 @@ type utteranceSender interface {
 	Send(ctx context.Context, utt audio.Audio, lang string) (audio.Audio, error)
 }

+// keywordGate answers whether the keyword has just been spoken. The
+// production one is wakeWord; tests substitute a recorder, because a gate that
+// can only be exercised with three ONNX files is a gate nobody tests.
+type keywordGate interface {
+	Feed(frame []int16) bool
+	Reset()
+	Score() float64
+}
+
 // bargeInConfig holds the two numbers barge-in needs. Zero Frames disables
 // barge-in entirely — the half-duplex gate still runs.
 type bargeInConfig struct {
@@ -63,6 +72,14 @@ type session struct {
 	// whenever playback ends.
 	loudFrames int

+	// wake is the keyword gate, or nil when no model was loaded. wakeUntil is
+	// how long a keyword stays good for: he says "Мэйвен" and then a sentence,
+	// and the VAD does not close the utterance until he stops, so the window
+	// has to outlive the word by the length of what follows it.
+	wake       keywordGate
+	wakeWindow time.Duration
+	wakeUntil  time.Time
+
 	// pending holds a nudge the push receiver handed over, waiting for the
 	// capture loop to speak it. It is the one field written from another
 	// goroutine, hence the mutex; everything else in this struct belongs to
@@ -76,6 +93,8 @@ type session struct {
 	bargeIns   int // times playback was cut because he spoke over her
 	sent       int // utterances shipped to the daemon
 	nudges     int // proactive pushes spoken through the speaker
+	wakes      int // times the keyword opened the gate
+	ignored    int // complete utterances dropped because the keyword was absent

 	// loudSum and loudSeen accumulate the energy of suppressed frames, so
 	// the operator can read what the room actually measures and set
@@ -88,6 +107,12 @@ func newSession(vad *VAD, p player, s utteranceSender, lang string, barge bargeI
 	return &session{vad: vad, player: p, sender: s, lang: lang, barge: barge, now: time.Now}
 }

+// UseWakeWord puts the keyword gate in front of dispatch. Without it every
+// utterance is shipped, which is what mavwaked did before V-487 stage two.
+func (s *session) UseWakeWord(w keywordGate, window time.Duration) {
+	s.wake, s.wakeWindow = w, window
+}
+
 // frameDuration is the wall time one captured frame represents.
 const frameDuration = defaultFrameMs * time.Millisecond

@@ -147,6 +172,7 @@ func (s *session) feed(ctx context.Context, frame []byte) error {
 		s.bargeIns++
 		s.loudFrames = 0
 		s.vad.Reset()
+		s.resetWake()
 		log.Printf("mavwaked: barge-in — stopped playback")
 		s.replayRecent()
 		return nil
@@ -157,13 +183,28 @@ func (s *session) feed(ctx context.Context, frame []byte) error {
 	if s.loudFrames != 0 {
 		s.loudFrames = 0
 		s.vad.Reset()
+		// The wake word saw nothing during playback, so what it holds is from
+		// before she spoke. Judging what he says next on it would score a
+		// sentence that ended a reply ago.
+		s.resetWake()
 	}

 	if s.startPendingNudge() {
 		return nil
 	}

-	utt, state := s.vad.Feed(PCMToI16(frame))
+	// The keyword is scored on the same frames the VAD sees, and only on the
+	// ones that reach here: every path above returns while she is speaking, so
+	// her own voice saying "Мэйвен" cannot wake her.
+	pcm := PCMToI16(frame)
+	if s.wake != nil && s.wake.Feed(pcm) {
+		s.wakes++
+		s.wakeUntil = s.now().Add(s.wakeWindow)
+		log.Printf("mavwaked: keyword heard (score %.3f), listening for %s",
+			s.wake.Score(), s.wakeWindow)
+	}
+
+	utt, state := s.vad.Feed(pcm)
 	if state == StateSpeech || utt.Bytes == nil {
 		return nil
 	}
@@ -218,6 +259,25 @@ func (s *session) startPendingNudge() bool {
 	return true
 }

+// awake reports whether an utterance ending now was addressed to her.
+//
+// With no wake word loaded every utterance is, which is exactly what mavwaked
+// did before this gate existed. An operator with no model file gets the old
+// daemon rather than a daemon that refuses to hear anything.
+func (s *session) awake() bool {
+	if s.wake == nil {
+		return true
+	}
+	return s.now().Before(s.wakeUntil)
+}
+
+// resetWake drops the gate's streaming state when there is a gate.
+func (s *session) resetWake() {
+	if s.wake != nil {
+		s.wake.Reset()
+	}
+}
+
 // keepRecent stores a copy of one barge-in trigger frame, keeping at most
 // barge.Frames of them.
 func (s *session) keepRecent(frame []byte) {
@@ -258,6 +318,19 @@ func (s *session) replayRecent() {
 // whole backlog straight into the VAD, and a Send error did the same on every
 // failed turn, so a dead socket drove a retry loop off nothing but backlog.
 func (s *session) dispatch(ctx context.Context, utt audio.Audio) error {
+	if !s.awake() {
+		s.ignored++
+		log.Printf("mavwaked: utterance ignored, keyword not heard (%.2fs, %d ignored so far)",
+			utt.Duration(), s.ignored)
+		s.vad.Reset()
+		s.resetWake()
+		return nil
+	}
+	// One keyword, one turn. A window that renewed itself on every reply would
+	// leave the microphone open for as long as he kept talking, which is the
+	// state this gate exists to end.
+	s.wakeUntil = time.Time{}
+
 	log.Printf("mavwaked: utterance complete (%.2fs, %d bytes), sending...", utt.Duration(), len(utt.Bytes))
 	start := s.now()
 	reply, err := s.sender.Send(ctx, utt, s.lang)
@@ -286,6 +359,7 @@ func (s *session) dispatch(ctx context.Context, utt audio.Audio) error {
 // recorded before she started speaking.
 func (s *session) dropBacklog(start time.Time) {
 	s.vad.Reset()
+	s.resetWake()
 	s.loudFrames = 0
 	s.recent = s.recent[:0]
 	if elapsed := s.now().Sub(start); elapsed > 0 {