Pitch candidate selection method for multi-channel pitch detectors

• US 20040158462A1
• Filed: 12/10/2003
• Published: 08/12/2004
• Est. Priority Date: 06/11/2001
• Status: Abandoned Application

• Current Assignee: Andrew Fort, Glen J. Rutledge, Peter Lupini
• Original Assignee: Andrew Fort, Glen J. Rutledge, Peter Lupini
• Inventors: Lupini, Peter, Rutledge, Glen J., Fort, Andrew
• Application Number:
  US10/480,690
• Publication Number:
  US 20040158462A1
• Time in Patent Office: Days
• US Class Current: 704/207
• CPC Class Codes: G10L 25/30 using neural networks
• CPC Class Codes: G10L 25/90 Pitch determination of speech signals

Abstract

An improved method of performing channel selection in multi-channel pitch detection systems. For each channel, several features are computed using the input signal and the value of the pitch candidate from the channel. The resulting feature vector is used to evaluate a multi-variate likelihood function which defines the likelihood that the pitch candidate represents the correct pitch. The final pitch estimate is then taken to be the pitch candidate with the highest likelihood of being correct, or the mean (or median) of the pitch candidates with likelihoods above a given threshold. The functional form of the likelihood function can be defined using several different parametric representations, and the parameters of the likelihood function can be advantageously derived in an automated manner using signals having pitch labels that are considered to be correct. This represents a significant improvement over previous channel selection methods where the parameters are chosen laboriously by hand.

Claims

1. A method for estimating the pitch of a signal comprising:

determining multiple pitch candidates from said signal.

determining multiple signal features (i.e. a feature vector) for each of the pitch candidates.

estimating the parameters of a likelihood function on the feature space which returns the likelihood that a pitch candidate is correct based on the position of its corresponding feature vector.

determining the likelihood that each pitch candidate is correct by evaluating the likelihood function at the position defined by each of the said pitch candidate'"'"'s feature vectors.

determining the output pitch to be a function of the individual pitch candidates and their likelihood of being correct.

2. The method of claim 1, where the parameters of the likelihood function are estimated using expert knowledge.

3. The method of claim 1, where the parameters of the likelihood function are estimated using a “

learning from data”

method.

4. The method of claim 3 where the “

learning from data”

method operates in an adaptive mode.

5. The method of claim 4, where the adaptive mode uses the EM algorithm to update the parameters of the likelihood function.

6. The method of claim 3, where the “

learning from data”

method uses labelled training data and operates in batch mode.

7. The method of claim 6, where the training data is obtained using a method comprising:

obtaining a training signal s(t), and a corresponding pitch signal τ

^c(t) that is considered to be the correct pitch of s(t) for each instance in time, where regions of the signal s(t) that are not pitched have been clearly marked and are ignored.

determining several (Q) pitch candidates and their corresponding feature vectors from the training signal s(t) at several (Ñ

) instances in time to obtain the following sequences

{τ

₁(t_n),τ

₂(t_n), . . . ,τ

_Q(t_n)},{x₁(t_n),x₂(t_n), . . . ,x_Q(t_n)},

for n=1, . . . , Ñ

.

determining the correct pitch using the pitch signal τ

^c(t) at the same instances in time to produce the sequence {τ

^c(t_n)}, for n=1, . . . , Ñ

.

assigning a pitch candidate τ

_q(t_n) to the correct class y_q(t_n)=ω

⁽¹⁾ if it is less than some pre-defined threshold ε

from the correct pitch τ

^c(t_n) for that time instance, and otherwise assigning the pitch candidate to the incorrect class y_q(t_n)=ω

⁽⁰⁾.

ignoring the order of the pitch candidates and the time sequence, and matching each feature vector x_q(t_n) with its corresponding class label y_g(t_n) to form sequence of pairs {x[n],y[n]}, for n=1, . . . , N, where N=QÑ

.

8. The method of claim 6, where the batch mode uses a neural network to estimate the parameters of the likelihood function.

9. The method of claim 8, where the functional form of the neural network consists of a multi-layer perceptron network.

10. The method of claim 8, where the functional form of the neural network consists of a radial basis function network.

11. The method of claim 6, where the batch mode uses a Bayesian formulation to define the functional form of the likelihood function as the a posteriori probability of the pitch candidate belonging to the correct class.

12. The method of claim 11, where the pdƒ

functions for the correct and incorrect classes are estimated using a density estimation method.

13. The method of claim 12, where the pdƒ

functions for the incorrect and correct class are estimated using a Gaussian mixture model.

16. The method of claim 1, where at least one of the features in the feature vector are computed using a cepstral-domain representation of the signal ƒ

_cep(τ

).

17. The method of claim 16, where the feature is computed for a pitch candidate as the cepstral value at the quefrency given by the pitch candidate ƒ

_cep(τ

_q(t_n)), divided by the maximum value in the cepstrum over a pre-defined range max<sub>τ

ε

τ</sub>

ƒ

_cep(τ

).

18. The method of claim 16, where the feature is computed for a pitch candidate as the cepstral value at the quefrency given by an integer multiple M of the pitch candidate ƒ

_cep(M.τ

_q(t_n)), or an integer fraction 1/M of the pitch candidate ƒ

_cep(τ

_q(t_n)/M) divided by the maximum value in the cepstrum over a pre-defined range max<sub>τ

ε

τ</sub>

ƒ

_cep(τ

).

19. The method of claim 1, where at least one of the features in the feature vector are computed using a frequency-domain representation of the signal.

20. The method of claim 1, where at least one of the features in the feature vector are computed using a time-domain representation of the signal.

21. The method of claim 1, where at least one of the features in the feature vector are computed using an autocorrelation-domain representation of the signal.

22. The method of claim 1, where at least one of the features in the feature vector are computed using the excitation signal which results from inverse filtering the signal with a filter from an LPC model.

23. The method of claim 1, where at least one of the features in the feature vector are computed using time-delayed information in the signal.

24. The method of claim 1, where at least one of the features in the feature vector are computed based on measured signal properties that are independent of the pitch candidate and the method used to compute the pitch candidate.

25. The method of claim 1, where the output pitch is computed by first removing all pitch candidates below a pre-defined likelihood level, and then averaging or taking the median of the remaining pitch candidates.

14. The method of 13, where the parameters of the Gaussian functions in the model are determined completely from the data.

15. The method of 13, where the pdƒ

of the correct class is modelled as a single Gaussian, and the pdƒ

of the incorrect class is modelled as the sum of three or more Gaussians representing pitch candidates corresponding to 1/2 the correct pitch, 2 times the correct pitch, possibly higher or lower integer multiples, and a catch all class for pitch candidates that correspond to an incorrect pitch but do not fall into one of the pre-defined categories.