File: SpeechRecognition-phrases-manual.https.html

package info (click to toggle)
firefox 144.0-1
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 4,637,504 kB
  • sloc: cpp: 7,576,692; javascript: 6,430,831; ansic: 3,748,119; python: 1,398,978; xml: 628,810; asm: 438,679; java: 186,194; sh: 63,212; makefile: 19,159; objc: 13,086; perl: 12,986; yacc: 4,583; cs: 3,846; pascal: 3,448; lex: 1,720; ruby: 1,003; exp: 762; php: 436; lisp: 258; awk: 247; sql: 66; sed: 53; csh: 10
file content (103 lines) | stat: -rw-r--r-- 3,825 bytes parent folder | download | duplicates (4)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
<!DOCTYPE html>
<html lang="en">
<meta name="timeout" content="long">
<title>SpeechRecognition Phrases</title>

<script src="/resources/testdriver.js"></script>
<script src="/resources/testdriver-vendor.js"></script>
<script src="/resources/testharness.js"></script>
<script src="/resources/testharnessreport.js"></script>

<script>
async function getAudioTrackFromFile(filePath) {
    const audioContext = new AudioContext();
    const response = await fetch(filePath);
    const arrayBuffer = await response.arrayBuffer();
    const audioBuffer = await audioContext.decodeAudioData(arrayBuffer);
    const source = audioContext.createBufferSource();
    source.buffer = audioBuffer;

    const destination = audioContext.createMediaStreamDestination();
    source.connect(destination);
    source.start();

    return destination.stream.getAudioTracks()[0];
}

promise_test(async (t) => {
    window.SpeechRecognition = window.SpeechRecognition || window.webkitSpeechRecognition;

    // Install en-US for on-device speech recognition.
    const installOptions = { langs: ["en-US"], processLocally: true };
    const installPromise = test_driver.bless(
        "Install on-device en-US speech recognition",
        () => SpeechRecognition.install(installOptions)
    );
    assert_true(
        installPromise instanceof Promise,
        "SpeechRecognition.install() should return a Promise."
    );
    const installResult = await installPromise;
    assert_true(
        installResult,
        "SpeechRecognition.install() for en-US should resolve with true."
    );

    // Verify the audio track for recognition context exists.
    const audioTrack = await getAudioTrackFromFile("/media/recognition_context.mp3");
    assert_true(
        audioTrack instanceof MediaStreamTrack,
        "Audio track should be a valid MediaStreamTrack"
    );

    // Create the first speech recognition with a mode that does not support contextual biasing.
    // Note that this may vary between browsers in the future.
    const recognition1 = new SpeechRecognition();
    recognition1.processLocally = false;
    recognition1.lang = "en-US";

    recognition1.onerror = function(event) {
        assert_equals(
            event.error,
            "phrases-not-supported",
            "First speech recognition should throw a phrases-not-supported error"
        );
    };

    recognition1.phrases.push(new SpeechRecognitionPhrase("test", 1.0));

    // Create the second speech recognition with a mode that supports contextual biasing.
    const recognition2 = new SpeechRecognition();
    recognition2.processLocally = true;
    recognition2.lang = "en-US";

    // On-device speech recognition should not throw an error.
    recognition2.onerror = t.unreached_func("recognition2 should not error");

    recognition2.phrases = [
        new SpeechRecognitionPhrase("ASIC", 3.0),
        new SpeechRecognitionPhrase("FPGA", 3.0)
    ];

    const recognitionPromise = new Promise((resolve) => {
        recognition2.onresult = (event) => {
            const transcript = event.results[0][0].transcript;
            const words = transcript.toLowerCase().split(' ');
            // Resolve when the last word is "expectations".
            if (words.length > 0 && words[words.length - 1] === "expectations") {
                resolve(transcript);
            }
        };
    });
    recognition2.start(audioTrack);

    const transcript = await recognitionPromise;
    assert_equals(
        transcript.toLowerCase(),
        "the report confirmed that the asic's throughput and " +
        "the fpga's latency were both below expectations",
        "Second speech recognition should correctly recognize the phrases"
    );
}, "SpeechRecognition should recognize speech with the given contextual information.");
</script>
</html>