Download - Detection of acoustic landmark
![Page 1: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/1.jpg)
1
Detection of Acoustic Landmarks for Speech Processing with High
Resolution M.Tech Credit Seminar
Pushpa Gothwal (09307054)Supervisor: Prof. P. C. Pandey
Electrical Engineering DepartmentNovember 2009
![Page 2: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/2.jpg)
2
Introduction Landmarks and their categorization Landmark detection methods
1. Manual labeling of landmarks2. Detection of abrupt consonant and abrupt landmarks3. Stop consonant landmark detection method
Summary and Future work
Outline
2
![Page 3: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/3.jpg)
3
Introduction
Perception of speech under adverse listening conditions is improved by processing of speech
Landmark detection is needed for processing
Aim : To study 3 different methods of landmark detection and compare their temporal resolution
3
![Page 4: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/4.jpg)
4
Introduction
Landmarks and their categorization Landmark detection methods
1. Manual labeling of landmarks
2. Detection of abrupt consonant and abrupt landmarks
3. Stop consonant landmark detection method Summary and Future work
4
![Page 5: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/5.jpg)
5
.
Landmarks is the region where the spectral discontinuity in speech.
They can be categorized as:– Abrupt Consonantal :It is the closure and release of
constriction. Example- /able/ – Abrupt: It shows the change in sound due to glottal
activity. Example- /paint/– Nonabrupt: It marks the transition between semivowel
to vowel and vice versa. Example-/away/– Vocalic: It occurs when the vocal cord is extremely
open for a vowel. Example-/bat/
What is a Landmark?
![Page 6: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/6.jpg)
6
An illustration of landmarks. AC = abrupt-consonantal, A = abrupt, N = nonabrupt, V = vocalic (Lui 1996)
![Page 7: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/7.jpg)
7
Introduction Landmarks and their categorization Landmark detection methods
1. Manual labeling of landmarks2. Detection of abrupt consonant and abrupt landmarks
3. Stop consonant landmark detection method Summary and Future work
7
![Page 8: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/8.jpg)
8
Manual labeling of landmarks
Spectrogram of /aba/ (Prat)
![Page 9: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/9.jpg)
9
Introduction Landmarks and their categorization Landmark detection methods
1. Manual labeling of landmarks
2. Detection of abrupt consonant and abrupt landmarks3. Stop consonant landmark detection method
Summary and Future work
9
![Page 10: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/10.jpg)
10
Detection of abrupt consonant and abrupt landmarks
It detects two landmarks Spectrum is divided into 6 bands
Band1. 0.0-0.4 Khz 2. 0.8-1.5 3. 1.2-2.0 4. 2.0-3.5 5. 3.5-5.0 6. 5.0-8.0 Band 1-Monitor glottal activityBand 2-5-Monitor Closure and release of sonorantBand 6-Monitor the stop
![Page 11: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/11.jpg)
11Landmark detection algorithm (Lui 1996)
Detection of abrupt consonant and abrupt landmarks (cont.)
![Page 12: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/12.jpg)
12
Spectrogram of “the money is coming today". The middle figure shows energy of band 1; and bottom figure shows ROR of band.(Lui,1996)
Detection of abrupt consonant and abrupt landmarks (cont.)
![Page 13: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/13.jpg)
13
Introduction Landmarks and their categorization Landmark detection methods
1. Manual labeling of landmarks
2. Detection of abrupt consonant and abrupt landmarks
3. Stop consonant landmark detection method Summary and Future work
13
![Page 14: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/14.jpg)
14
Pass I
Step 1 : Spectrum is divided into 5 bandsBand Frequency (kHz) 1 0.0-0.4 (Monitor glottal vibration) 2 0.4-1.2 3 1.2-2.0 4 2.0-3.5 5 3.5-5.0
(Consonant closure andrelease)
Stop consonant landmark detection method
![Page 15: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/15.jpg)
15
Short time spectral analysis
Computation of energy peaks and centroids
Computation of RORs energy and centroid
Computation of spectral transition index
Landmark localization
Wavelet decomposition around landmarks
Computation of short time energy and ZCR
Computation of energy and ZCR RORs
Landmark localization
Landmark(Pass 1)
Landmark (Pass 2)
Pass 1 Pass2
Processing stage for landmark detection (Arjun et al., 2008)
speech
![Page 16: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/16.jpg)
16
Step 2 - Computation of energy peaks and centroid in frequency bands
where k1 and k2 upper and lower frequency index for band b,n frame.
Centroid frequency is k2 k2
fc(b,n)= ∑ k|Xn(k)|2 / ∑ |Xn(k)|2 fs/N (2)
k=k1 k=k1
Ep (b, n) = 10 log10 (max [|X n (k)|] 2), k1 ≤ k ≤k2 (1)
Stop consonant landmark detection method (cont.)
![Page 17: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/17.jpg)
17
Step 3-Computation of energy and centroid RORs
E'p(b,n) = | Ep(b, n+K) − Ep(b,n−K)| (3)
f'c(b, n) = | fc(b, n+K) − fc(b,n−K) | (4)
Stop consonant landmark detection method (cont.)
![Page 18: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/18.jpg)
18
Step 4-Computation of transition index for energy and centroid frequency
5 Tec(n) = 1/5∑E’pn(p, n)f’cn(b,n) (5)
b=1
Stop consonant landmark detection method (cont.)
![Page 19: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/19.jpg)
19 Waveform for /uka/ , ROR for band1(b), band2(c), band3(d) (Arjun et al.,2008)
Stop consonant landmark detection method (cont.)
![Page 20: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/20.jpg)
20 Processing results /uka/ of (Arjun et al., 2008)
Stop consonant landmark detection method (cont.)
![Page 21: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/21.jpg)
21
(a) Windowed segment used in second pass, (b) energy and ZCR ROR’s of level 1, (c) ROR’s of level 2, and (d) transition index Tez computed from ROR’s in (b) and (c) (Arjun et.al.2008)
Stop consonant landmark detection method (cont.)
![Page 22: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/22.jpg)
22
Pass2:
Step1-Compute the wavelet decomposition for segmenting the speech
Step2-Compute the energy and Zero Crossing Rate (ZCR)
Step3-Compute the ROR for energy and ZCR
Stop consonant landmark detection method (cont.)
![Page 23: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/23.jpg)
23
Introduction Landmarks and their categorization Landmark detection methods
1. Manual labeling of landmarks
2. Detection of abrupt consonant and abrupt landmarks
3. Stop consonant landmark detection method
Summary and Future work
23
![Page 24: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/24.jpg)
24
Summary
The first method of landmark detection is time consuming and tedious. Moreover the resolution is also very poor.
The second method is relatively faster but it also gives poor temporal resolution.
The third method gives very high temporal resolution at a faster pace.
24
![Page 25: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/25.jpg)
25
Future Work
To focus on the algorithms for landmark detection in speech and to improvise them to implement in the phone-based recognition system.
![Page 26: Detection of acoustic landmark](https://reader036.vdocument.in/reader036/viewer/2022081520/58a46c331a28abb8288b6fab/html5/thumbnails/26.jpg)
26
REFERENCES[Lui 1996] S. A. Liu, “Landmark detection for distinctive feature based speech recognition,” J. acoust. Soc. Am., vol. 100, no. 5, pp. 3417-3430. [Arjun et al., 2008] A.R.Jayan,P.C.Pandey and ,”Detection of Acoustic Landmarks with high resolution for Speech Processing” Procc,14th
National conf.communication.
[Alani et al.,1999] A.Alani and M.Deriche, “A novel approach to speech segmentation using the wavelet transform,” in proc.5th int.stmp.signal Processing and Applications.(ISSSPA’99),127-129.
[OS 2001] D. O'shaughnesey, Speech Communications: Humans and Machine, University Press (India).
[L.R., 2008] L. R. Rabiner, R. W. Schafer, Digital Processing of Speech Signals, Pearson Education Inc. and Dorling Kindersley Publishing Inc., India.