tamil words speech synthesis in cochlear implant using acoustic model
DESCRIPTION
GUIDED BY T.JAYASANKAR, ASST.PROFESSOR OF ECE, ANNA UNIVERSITY OF TIRUCHIRAPPALLI. PRESENTED BY C.SENTHILKUMAR, REG.NO:810011992018, M.E(MBCBS),COM SYSTEM,VI MODULE. . TAMIL WORDS SPEECH SYNTHESIS IN COCHLEAR IMPLANT USING ACOUSTIC MODEL. - PowerPoint PPT PresentationTRANSCRIPT
TAMIL WORDS SPEECH SYNTHESIS IN COCHLEAR IMPLANT USING ACOUSTIC MODEL
GUIDED BYT.JAYASANKAR,ASST.PROFESSOR OF ECE,ANNA UNIVERSITY OF TIRUCHIRAPPALLI.
PRESENTED BYC.SENTHILKUMAR,
REG.NO:810011992018,M.E(MBCBS),COM SYSTEM,VI MODULE.
OBJECTIVE
A cochlear implant (CI) is a surgically implanted electronic device that provides a sense of sound to a person who is profoundly deaf or severely hard of hearing.
The main objective of this work is to develop the system that reproduces the incoming sound/speech signals as naturally as possible
LITERATURE SURVEY S.NO TITLE AUTHORS YEAR & PUBLICATION CONCEPT
1 Estimation of Vowel Recognition WithCochlear Implant Simulations
Chuping Liu and Qian-Jie Fu IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL. 54, NO. 1, JANUARY 2007
In this paper, Mel-frequency cepstrum coefficients(MFCCs) were used to estimate the acoustic vowel space forvowel stimuli processed by the CI simulations.
2 Improving Speech Intelligibility in Cochlear Implants usingAcoustic Models
P. VIJAYALAKSHMI, T. NAGARAJAN and PREETHI MAHADEVAN
ISSN: 1790-5052 Issue 4, Volume 7, October 2011
In this paper to improve the perceptualquality of the speech generated by a CI model, system specific parameters are analyzed by developinguniform bandwidth filterbank-based acoustic CI models
3 MIMICKING THE HUMAN EAR Philipos C.Loizon IEEE SIGNAL PROCESSING MAGAZINE1053-5888/98/$10.000 1998IEEE
An overview of Signal- Processing Strategies for converting sound into Electrical sgnals in cochlear implants
SYSTEM DESIGN
Speech Data Collection
Tamil words are recorded from a male speaker at a sampling frequency of 16 kHz with a head mounted carbon microphone of frequency range 20 Hz – 20 kHz using s PRAAT tool
CHANNEL VOCODER BASED ACOUSTIC MODEL
General block Diagram
ANALYZER SYNTHESIZER
ACOUSTIC MODEL
INPUTSPEECH
SYNTHETICSPEECH
CHANNEL VOCODER
Uniform bandwidth filter bank method Critical bandwidth filter bank method
CHANNEL VOCODER ANALYZER(UNIFORM BANDWIDTH)
CONT…Acoustic model parameters Sampling Frequency : 16000Hz Frequency Range : 0-8200Hz Filter Type : IIR – Chebyshev type-
2 No. of Channels : 21 (1 LPF +20 BPF) Bandwidth : 400Hz Order of filter : 5
CONT..Filter order Mean squared
difference1 0.00332 0.00323 0.00314 0,00315 0.00306 1.4861e+2387 4.3540e+3008 1.6547e+2999 2.7285e+29610 3.3515e+299
CHANNEL VOCODER SYNTHESIZER(UNIFORM BANDWIDTH)
WAVEFORM OF THE TAMIL WORD /அம்மா/
FILTERED SIGNAL & ITS ENVELOPE
TRAIN OF IMPULSE
Pitch period =0.0063sec
MODULATED AND SYNTHESIZED FILTER OUTPUT
ORIGINAL & SYNTHESIZED SPEECH SIGNAL
CRITICAL BANDWIDTH FILTER BANK BASED ACOUSTIC CI MODEL
Critical band is the smallest band of frequencies that activate the same part of basilar membrane and human ear can able to discriminate two tones that differ in critical bands.
DESIGN OF CI MODEL BASED ON CRITICAL BANDS
Filter bank is designed based on critical bands of the human auditory system.
The critical band of each auditory band-pass filter is computed using equivalent rectangular bandwidth (ERB).
If the center frequencies (fc) of filters are known, then the corresponding ERBs are calculated using the following formula,
ERB=24.7((0.00437*fc) +1) (1)
INPUT WORD/அம்மா/
WAVEFORM OF INPUT AND SYNTHESIZED SPEECH FOR THE TAMIL WORD /அம்மா/
MEAN SQUARE DIFFERENCE BETWEEN UNIFORM BANDWIDTH FILTER-BASED CI MODEL AND AUDITORY
CI MODEL
Uniform Bandwidh Model Critical Bandwidth Model0
0.0005
0.001
0.0015
0.002
0.0025
0.003
0.0035
0.004
0.0045
0.005
Mean square Difference
அம்மா
அன்பு
மலர்
மரம்
முகம்
நிறம்
பணம்
MEAN OPINION SCORE(MOS) FOR UBW & CBW SYSTEM
UBW CBW4.054.1
4.154.2
4.254.3
4.354.4
4.454.5
4.55MEAN OPINION SCORE
MEAN OPINION SCORE
CONCLUSION
The Critical band CI model is performed well when compared with the Uniform bandwidth filter bank method based on the mean square difference & Mean opinion score.
REFERENCES P. Vijayalakshmi , T. Nagarajan and Preethi Mahadevan,(2011), “ Improving Speech
Intelligibility in Cochlear Implants using Acoustic Models’’, WSEAS TRANSACTIONS on SIGNAL PROCESSING, Issue 4, Volume 7, October 2011, pp. 131 – 144.
Gladston, A.R.; Vijayalakshmi, P.; Thangavelu, N., "Improving speech intelligibility in cochlear implants using vocoder-centric acoustic models," Recent Trends In Information Technology (ICRTIT), 2012 International Conference on , vol., no., pp.66,71, 19-21 April 2012.
D. K. Eddington, W. M. Rabinowitz, and L.Dellzome, “Sound Processing for Cochlear Implants”, in Proceedings of International IEEE EMBC, 2001, pp. 3449- 3452.
B. Gold and N. Morgan, “Speech and audio signal processing - processing and perception of speech and music”. John Wiley and Sons. Inc., 2000.
P. C. Loizou, “Speech processing in vocoder-centric cochlear implants” Cochlear and Brainstem Implants. Adv Otorhinolaryngol. Basel, Karger, vol 64, pp 109–143, 2006.
P.C. Loizou, ”Mimicking the human ear” IEEE Signal Processing magazine, vol. 15, no. 5, Sep. 1998, pp. 101-130
Thank You