Packages

final case class Viterbi(mul: D = 1.0, add: D, numStates: I, numFrames: I = -1) extends SingleOut[Int] with Product with Serializable

A UGen performing a generalized Viterbi algorithm. The Viterbi algorithm tries to find the best path among sequences of states, by evaluating transition probabilities. It runs over a predefined number of frames, accumulating data of different states. It maximizes the likelihood of the terminal state, and then backtracks to reconstruct the likely path (sequence of states). The output is the sequence of state indices (from zero inclusive to numStates exclusive).

Note: This UGen must run until numFrames or the inputs are exhausted, before it can begin outputting values.

This implementation is generalized in the sense that instead of the canonical matrices "sequences of observations", "initial probabilities", "transition matrix", and "emission matrix", it takes two large matrices mul and add that contain the equivalent information. These two matrices allow the UGen to operate in two different modes:

- multiplicative (as in the Wikipedia article) by damping the probabilities over time - accumulative (as used in Praat for pitch tracking) by adding up the weights (if you have "costs", feed in their negative values).

Basically the internal delta matrix is created by the update function delta = (delta_prev * mul) + add (with the corresponding matrix indices).

The initial delta state is zero. Therefore, in order to provide the initial state, you obtain an initial vector v by providing an add matrix of numStates x numStates cells, which is zero except for the first column filled by v (alternatively, each row filled with the next value of v, or a diagonal matrix of v; if v can take negative value, make sure to fill the initial numStates x numStates completely by duplicating v).

For the classical data, set add just to the initial matrix as explained above (multiplying emitted first observations with initial probabilities), and then use exclusively mul by passing in emitted observations multiplied by their transition probabilities:

mul[t][i][j] = transitionProb[i][j] * emissionProb[observation[t]][i]

See https://en.wikipedia.org/wiki/Viterbi_algorithm

mul

the generalized multiplicative matrix (combining transition probabilities, emission probabilities and observations). If only accumulation is used, set this to 1.0.

add

the generalized accumulative matrix (combining transition probabilities, emission probabilities and observations). If only multiplication is used, set this to provide the initial state (see above), followed either by zeroes or by terminating the signal.

numStates

the number of different states, as reflected by the inner dimensions of matrices mul and add.

numFrames

the number of observations. If -1, the UGen runs until the input is exhausted. This happens when both mul and add end. see StrongestLocalMaxima see PitchesToViterbi

Linear Supertypes
Serializable, SingleOut[Int], SomeOut[Int, StreamOut], GE.Lazy[Int], GE[Int], UGenSource[UGenInLike[Int], StreamOut], Expander[UGenInLike[Int]], Lazy, Product, Equals, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. Viterbi
  2. Serializable
  3. SingleOut
  4. SomeOut
  5. Lazy
  6. GE
  7. UGenSource
  8. Expander
  9. Lazy
  10. Product
  11. Equals
  12. AnyRef
  13. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. Protected

Instance Constructors

  1. new Viterbi(mul: D = 1.0, add: D, numStates: I, numFrames: I = -1)

    mul

    the generalized multiplicative matrix (combining transition probabilities, emission probabilities and observations). If only accumulation is used, set this to 1.0.

    add

    the generalized accumulative matrix (combining transition probabilities, emission probabilities and observations). If only multiplication is used, set this to provide the initial state (see above), followed either by zeroes or by terminating the signal.

    numStates

    the number of different states, as reflected by the inner dimensions of matrices mul and add.

    numFrames

    the number of observations. If -1, the UGen runs until the input is exhausted. This happens when both mul and add end. see StrongestLocalMaxima see PitchesToViterbi

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##: Int
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  4. val add: D
  5. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  6. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.CloneNotSupportedException]) @native() @HotSpotIntrinsicCandidate()
  7. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  8. final def getClass(): Class[_ <: AnyRef]
    Definition Classes
    AnyRef → Any
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  9. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  10. def makeUGen(args: IndexedSeq[UGenIn[_]])(implicit b: Builder): UGenInLike[Int]
    Attributes
    protected
    Definition Classes
    ViterbiUGenSource
  11. def makeUGens(implicit b: Builder): UGenInLike[Int]

    Abstract method which must be implemented by creating the actual UGens during expansion.

    Abstract method which must be implemented by creating the actual UGens during expansion. This method is at most called once during graph expansion

    returns

    the expanded object (depending on the type parameter U)

    Attributes
    protected
    Definition Classes
    ViterbiExpander
  12. val mul: D
  13. final def name: String
    Definition Classes
    UGenSource
  14. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  15. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  16. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  17. val numFrames: I
  18. val numStates: I
  19. def productElementNames: Iterator[String]
    Definition Classes
    Product
  20. final def synchronized[T0](arg0: => T0): T0
    Definition Classes
    AnyRef
  21. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  22. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException]) @native()
  23. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])

Deprecated Value Members

  1. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.Throwable]) @Deprecated
    Deprecated

Inherited from Serializable

Inherited from SingleOut[Int]

Inherited from SomeOut[Int, StreamOut]

Inherited from GE.Lazy[Int]

Inherited from GE[Int]

Inherited from UGenSource[UGenInLike[Int], StreamOut]

Inherited from Expander[UGenInLike[Int]]

Inherited from Lazy

Inherited from Product

Inherited from Equals

Inherited from AnyRef

Inherited from Any

Ungrouped