Maven/cmd/mavwaked/wakeword_test.go

package main

import (
	"context"
	"testing"
	"time"
)

// fakeGate fires on demand instead of running three ONNX models. The gate's
// own arithmetic is measured on real audio in docs/evals; what these tests
// cover is the thing that decides whether an utterance is shipped.
type fakeGate struct {
	fireOn int // fire when this many frames have been fed, 0 never fires
	fed    int
	resets int
}

func (g *fakeGate) Feed(_ []int16) bool {
	g.fed++
	return g.fireOn > 0 && g.fed == g.fireOn
}
func (g *fakeGate) Reset()         { g.resets++ }
func (g *fakeGate) Score() float64 { return 1 }

// wakingSession wires a session whose gate fires on the first frame it sees.
func wakingSession(fireOn int, window time.Duration) (*session, *fakePlayer, *fakeSender, *fakeGate) {
	sess, p, snd := newTestSession(bargeInConfig{})
	g := &fakeGate{fireOn: fireOn}
	sess.UseWakeWord(g, window)
	return sess, p, snd, g
}

func TestKeywordlessSpeechNeverReachesSTT(t *testing.T) {
	sess, p, snd, g := wakingSession(0, 8*time.Second)
	speakThenPause(t, sess)

	if len(snd.sent) != 0 {
		t.Fatalf("sent %d utterances, want 0 — this is the whole point of V-487", len(snd.sent))
	}
	if sess.ignored != 1 {
		t.Errorf("ignored = %d, want 1", sess.ignored)
	}
	if p.plays != 0 {
		t.Errorf("plays = %d, want 0", p.plays)
	}
	if g.fed == 0 {
		t.Error("the gate was never fed a frame")
	}
}

func TestKeywordOpensTheGate(t *testing.T) {
	sess, p, snd, _ := wakingSession(1, 8*time.Second)
	speakThenPause(t, sess)

	if len(snd.sent) != 1 {
		t.Fatalf("sent %d utterances, want 1", len(snd.sent))
	}
	if sess.wakes != 1 {
		t.Errorf("wakes = %d, want 1", sess.wakes)
	}
	if sess.ignored != 0 {
		t.Errorf("ignored = %d, want 0", sess.ignored)
	}
	if p.plays != 1 {
		t.Errorf("plays = %d, want 1", p.plays)
	}
}

// One keyword buys one turn. Without this the microphone stays open for as
// long as he keeps talking, which is the state the gate exists to end.
func TestOneKeywordBuysOneTurn(t *testing.T) {
	sess, p, snd, _ := wakingSession(1, 8*time.Second)
	speakThenPause(t, sess)
	p.Stop()         // she finished her reply
	sess.discard = 0 // the backlog drain is not what this measures
	speakThenPause(t, sess)

	if len(snd.sent) != 1 {
		t.Fatalf("sent %d utterances, want 1: the second had no keyword", len(snd.sent))
	}
	if sess.ignored != 1 {
		t.Errorf("ignored = %d, want 1", sess.ignored)
	}
}

// The keyword is heard, then he says nothing for longer than the window. What
// he says after that is not addressed to her.
func TestTheKeywordExpires(t *testing.T) {
	sess, _, snd, _ := wakingSession(1, 500*time.Millisecond)
	now := time.Unix(1750000000, 0)
	sess.now = func() time.Time { return now }

	if err := sess.feed(context.Background(), silentBytes()); err != nil {
		t.Fatalf("feed: %v", err)
	}
	if sess.wakes != 1 {
		t.Fatalf("wakes = %d, want 1", sess.wakes)
	}
	now = now.Add(2 * time.Second)
	speakThenPause(t, sess)

	if len(snd.sent) != 0 {
		t.Fatalf("sent %d utterances, want 0 — the keyword had expired", len(snd.sent))
	}
}

// Barge-in cuts her off whether or not the keyword was heard. What he says
// after cutting her off still has to carry it.
func TestBargeInStillInterruptsHer(t *testing.T) {
	sess, p, _, g := wakingSession(0, 8*time.Second)
	sess.barge = bargeInConfig{RMS: 0.2, Frames: 3}
	p.playing = true
	loud := frameAt(0.35)
	for i := 0; i < 4; i++ {
		if err := sess.feed(context.Background(), loud); err != nil {
			t.Fatalf("feed %d: %v", i, err)
		}
	}
	if sess.bargeIns != 1 {
		t.Fatalf("bargeIns = %d, want 1", sess.bargeIns)
	}
	if p.stops != 1 {
		t.Errorf("stops = %d, want 1", p.stops)
	}
	if g.resets == 0 {
		t.Error("barge-in left pre-playback audio in the gate")
	}
}

// Her own reply must not wake her. Frames captured while the player runs never
// reach the gate, and the gate is cleared when playback ends.
func TestHerOwnVoiceNeverReachesTheGate(t *testing.T) {
	sess, p, _, g := wakingSession(1, 8*time.Second)
	p.playing = true
	for i := 0; i < 10; i++ {
		if err := sess.feed(context.Background(), frameAt(0.35)); err != nil {
			t.Fatalf("feed: %v", err)
		}
	}
	if g.fed != 0 {
		t.Fatalf("gate was fed %d frames while she was speaking, want 0", g.fed)
	}
	if sess.wakes != 0 {
		t.Errorf("wakes = %d, want 0", sess.wakes)
	}
}

// No model, no gate: the daemon behaves exactly as it did before V-487 stage
// two. An operator with a missing file gets yesterday's mavwaked, not one that
// refuses to hear anything.
func TestNoGateShipsEveryUtterance(t *testing.T) {
	sess, _, snd := newTestSession(bargeInConfig{})
	speakThenPause(t, sess)

	if len(snd.sent) != 1 {
		t.Fatalf("sent %d utterances, want 1", len(snd.sent))
	}
	if sess.ignored != 0 {
		t.Errorf("ignored = %d, want 0", sess.ignored)
	}
}

// A nil *wakeWord is the closed gate, not a crash and not an open one.
func TestNilWakeWordHearsNothing(t *testing.T) {
	var w *wakeWord
	if w.Feed([]int16{0, 0, 0}) {
		t.Error("a nil wake word reported the keyword")
	}
	if w.Score() != 0 {
		t.Error("a nil wake word reported a score")
	}
	w.Reset()
	w.Close()
}