Plot the first two formants across time

Reference no: EM131726724

Speech Signal Formant Estimation and Clustering

A MATLAB program to estimate Formants

A crude estimation of the location of the formants can be obtained using the LPC function in MATLAB along with z plane pole frequency evaluation. We approximate format frequency estimates with the angle of the poles. Run the program below to see a running estimate of poles in a speech file.

EXERCISE 1:

Use the program to generate the formants for say 200 frames of data.

Plot the first two formants across time (formants vs frame number).

Can you distinguish voiced vs unvoiced frames of speech from the signal signatures?

Create a table and provide the following information for frames 50-80.

EXERCISE 2:

Clustering of Formants

In the previous exercise, formant estimation from speech signal was introduced. You built a formant detector that estimates F1 and F2 from an incoming speech signal. In this exercise, you will study how to cluster different formants using a well-known clustering algorithm, the K-means clustering algorithm [4]. Clustering is an example of unsupervised machine learning algorithm. You will make use of the JDSP-HTML 5 for performing speech formant clustering.

Deliverables:

1. Write a brief report (3 pages max) summarizing both the content and results of the two parts. One report per group of two students.

PART 1: MATLAB Exercise on Formants

2. For the first MATLAB exercise include the plots, table.

3. Provide a paragraph that discusses the results and summarized what have you learned from the exercise.

(use the file provided on black board named: cleanspeech.wav)

PART 2. J-DSP Exercise

You will run the simulations for two data sets namely, "speech formant dataset 1" and "speech formant dataset 2".

4. What are the values of the cluster centroids after convergence for dataset 1 and dataset 2. Report the cluster centroid values for each of the mentioned vowels (report F1 and F2 values for both datasets).

5. What is the value of the within-cluster sum of squares observed after the convergence for dataset 1 and dataset 2? [ This value is obtained in the JDSP k-means block]

6. Include screen shots of clustering and screen shots of the convergence curve.

7. What is the deviation observed for each vowel's formant frequencies after convergence for dataset 1 and dataset 2 if the average values of the formants for the following vowels are as follows

aa: F1 = 750 Hz F2 = 940 Hz

ae: F1 = 750 Hz F2 = 1610 Hz

u: F1 = 250 Hz F2 = 595 Hz

i: F1 = 240 Hz F2 = 2400 Hz

[Report the differences in F1 and F2 values for each formant. For example, if the k-means block obtains the centroid value for the vowel /u/ as 200 Hz (F1) and 550 Hz (F2). Report the difference for F1 as 50 Hz (250 - 200) and difference for F2 as 45 Hz (595 - 550)]

8. Discuss how well the formants are clustered for dataset 1 and dataset 2.

9. Discuss briefly what you have learned from exercise 2.

Attachment:- Assignment Files.rar

Reference no: EM131726724

Questions Cloud

Describe the law of averages : A friend has three boys and would like to have a girl. She explains to you that the probability that her next baby will be a girl is very high.

What sampling method is most appropriate for study : You anticipate that their beliefs may differ from native born members of the community. What sampling method is most appropriate for this study

Code that finds and outputs the first x number : Code that finds and outputs the first x number of prime numbers, beginning with 2, where x is chosen by the user. Remember that a prime number is a number

How does murray define the concept of psychological need : Examine Murray's claim that psychological needs could underlie psychological disorders. Identify and discuss a particular need that could lead to a specific

Plot the first two formants across time : Plot the first two formants across time (formants vs frame number). Create a table and provide the following information for frames 50-80

Write a comment on the given situation : A friend, quite upset, calls you because she had a dream that a building had been bombed and she was helping to search for survivors.

Professional in charge of employee payroll for the practice : You are the administrative medical professional in charge of employee payroll for the practice.

Technology alternatives and implementation initiatives : Identify and describe the technology alternatives and implementation initiatives you would recommend to your organization's technology planning committee

Why and how would that mechanism offer protection : What security or networking mechanisms would you use to protect any Intranet servers you had? Why and how would that mechanism offer protection?

Reviews

len1726724

11/17/2017 1:28:00 AM

Detailed Question: Please make it in such away that i can understand how the solution is found. There is an audio file involved. DUE DATES: The report is due on on Blackboard. You may also submit it earlier. Bonus 10 points will be given for reports turned in on or before. Late reports will be penalized 25%. Reports after will not be accepted. The goal of this exercise is to reinforce several concepts in speech processing with the emphasis in linear predictive coding (LPC). The exercise starts with an introduction to speech spectra, pitch and formant estimation, and LPC analysis-synthesis.

Write a Review

Required(*) Message

User Account

All Pages