当前位置：首页 > 文章列表 > Golang > Go问答 > 使用 Go 语言进行声音检测

使用 Go 语言进行声音检测

来源：stackoverflow 2024-03-12 16:21:26 0浏览收藏

知识点掌握了，还需要不断练习才能熟练运用。下面golang学习网给大家带来一个Golang开发实战，手把手教大家学习《使用 Go 语言进行声音检测》，在实现功能的过程中也带大家重新温习相关知识点，温故而知新，回头看看说不定又有不一样的感悟！

问题内容

我正在致力于为 golang 声音检测器创建一个非常简单且轻量级的解决方案。我需要读取 mp3/mp4 音频流（目前使用文件）并执行当检测到比平时更大的声音时所具有的功能。我对 golang 比较陌生，对数字音频没有经验。我有下面的代码可以检测蜂鸣声，但不知道如何检测更大的噪音而不仅仅是蜂鸣声。任何帮助将不胜感激！！

package main

import (
    "encoding/binary"
    "fmt"
    "log"
    "math"
    "math/cmplx"
    "net/http"

    "os"

    "github.com/hajimehoshi/go-mp3"
    "github.com/hajimehoshi/oto"

    "github.com/mjibson/go-dsp/fft"

    "github.com/mjibson/go-dsp/window"
)

// const sampleRate = 44100
const toneFrequency = 440
const mp3file = "C:/Users/mmekaiel/Music/audio-samples/440Hz.mp3"

func serveHome(w http.ResponseWriter, r *http.Request) {
    w.Header().Set("Content-Type", "text/html")
    fmt.Fprint(w, "Hello world site!!")
}

func serveAudio(w http.ResponseWriter, r *http.Request) {
    w.Write([]byte("The tone-detect audio page!!"))

    if err := process(toneFrequency); err != nil {
        log.Fatal(err)
    }
}

func process(toneFreq int) error {
    f, err := os.Open(mp3file)
    if err != nil {
        return err
    }
    defer f.Close()

    d, err := mp3.NewDecoder(f)

    if err != nil {
        return err
    }

    p, err := oto.NewPlayer(d.SampleRate(), 2, 2, 8192)

    if err != nil {
        return err
    }

    defer p.Close()

    windowSize := 40 // window size in milliseconds
    windowSamples := int(float32(d.SampleRate()) * float32(windowSize) / 1000.0)

    // fftSize is the smallest power of 2 greater than or equal to windowSamples
    fftSize := int(math.Pow(2, math.Ceil(math.Log2(float64(windowSamples)))))

    spectralWidth := float64(d.SampleRate()) / float64(fftSize)
    targetIndex := int(float64(toneFreq) / spectralWidth)

    fmt.Printf("Sample Rate: %d\n", d.SampleRate())
    fmt.Printf("Length: %d[bytes]\n", d.Length())
    fmt.Printf("Window size: %d[samples]\n", windowSamples)
    fmt.Printf("FFT size: %d\n", fftSize)
    fmt.Printf("Spectral Line width: %v[hertz]\n", spectralWidth)
    fmt.Printf("Tone index: %d\n", targetIndex)

    b := make([]byte, windowSamples*4) // 2 bytes per sample, 2 channels
    w := make([]float64, fftSize)
    t := 0
    toneStart := -1

outerloop:
    for {
        // Read a window of samples
        bytesRead := 0
        for bytesRead < len(b) {
            n, err := d.Read(b[bytesRead:])
            if err != nil {
                break outerloop
            }
            bytesRead += n
        }

        // Convert to float (ignore second channel)
        for i := 0; i < len(b); i += 4 {
            w[i/4] = float64(int16(binary.LittleEndian.Uint16(b[i+0:i+2]))) / 32768.0
        }

        // Apply window function
        window.Apply(w, window.Hamming)

        // Perform FFT
        c := fft.FFTReal(w)

        // Compute the normalized magnitude
        r, _ := cmplx.Polar(c[targetIndex])
        r = r / float64(fftSize)

        // Look for tone
        toneDetected := r > 0.05 // Apply arbitrary threshold
        if toneDetected && toneStart < 0 {
            toneStart = t
        } else if !toneDetected && (toneStart >= 0) {
            fmt.Printf("Tone from %dms to %dms.\n", toneStart, t)
            toneStart = -1
        }

        t += windowSize
    }

    return nil
}

func main() {
    mux := &http.ServeMux{}

    mux.HandleFunc("/", serveHome)

    mux.HandleFunc("/audio", serveAudio)

    http.ListenAndServe(":8080", mux)
}