Add jitpack.io to your project's repositories:

allProjects {
  repositories {
    google()
    maven { url 'https://jitpack.io' }
  }
}

Add artifact to your project:

dependencies {
    implementation "com.github.MerlynMind:kotlin_speech_features:${version}"
}

A sample app is included in this repo to help understand the implementation.

1. Convert your audio signal in the form of a float array. (A demo provided in the sample app)
2. Initialize speech features

   private val speechFeatures = SpeechFeatures()

3. Perform any of the 4 operations:

   val result = speechFeatures.mfcc(MathUtils.normalize(wav), nFilt = 64)
   val result = speechFeatures.fbank(MathUtils.normalize(wav), nFilt = 64)
   val result = speechFeatures.logfbank(MathUtils.normalize(wav), nFilt = 64)
   val result = speechFeatures.ssc(MathUtils.normalize(wav), nFilt = 64)

4. The result will contain metrices with the expected features. Pass in these features for further processes (e.g. classification, speech recognition).

1. In XCode, go to File > Add Packages...
2. Paste in the URL of this repo in the search box
3. Select the package found
4. Click Add Package button

A sample app is included in this repo to help understand the implementation.

1. Convert your audio signal in the form of an KotlinIntArray and normalize it.

   import KotlinSpeechFeatures
   
   let signal = [Int](1...1000) // Example signal
   let normalized = MathUtils.Companion.init().normalize(sig: toKotlinIntArray(arr: signal))
   
   func toKotlinIntArray(arr: [Int]) -> KotlinIntArray {
       let result = KotlinIntArray(size: Int32(arr.capacity))
       for i in 0...(arr.count-1) {
           result.set(index: Int32(i), value: Int32(arr[i]))
       }
       return result
   }

2. Initialize speech features

   let speechFeatures = SpeechFeatures()

3. Perform any of the 4 operations:

   let result = speechFeatures.mfcc(signal: normalized, sampleRate: 16000, winLen: 0.025, winStep: 0.01, numCep: 13, nFilt: 64, nfft: 512, lowFreq: 0, highFreq: ni;, preemph: 0.97, ceplifter: 22, appendEnergy: true, winFunc: nil)
   let result = speechFeatures.fbank(signal: normalized, sampleRate: 16000, winLen: 0.025, winStep: 0.01, nFilt: 64, nfft: 512, lowFreq: 0, highFreq: nil, preemph: 0.97, winFunc: nil)
   let result = speechFeatures.logfbank(signal: normalized, sampleRate: 16000, winLen: 0.025, winStep: 0.01, nFilt: 64, nfft: 512, lowFreq: 0, highFreq: nil, preemph: 0.97, winFunc: nil)
   let result = speechFeatures.ssc(signal: normalized, sampleRate: 16000, winLen: 0.025, winStep: 0.01, nFilt: 64, nfft: 512, lowFreq: 0, highFreq: nil, preemph: 0.97, winFunc: nil)

4. The result will contain metrices with the expected features. Pass in these features for further processes (e.g. classification, speech recognition).