About this previous year paper
KEC078 – SPEECH PROCESSING
Complete Solved Question Paper
SECTION A
(Attempt all questions – 2 × 10 = 20 marks)
Q1(a) Key assumptions of acoustic theory of speech production
Speech is produced by an excitation source (voiced/unvoiced).
Vocal tract acts as a linear, time-varying filter.
Source and filter are independent.
Speech signal is quasi-stationary over short intervals.
Q1(b) Acoustic phonetics
Acoustic phonetics is the branch of phonetics that studies speech sounds as physical signals, analyzing properties like frequency, amplitude, spectrum, and duration.
Q1(c) Purpose of short-time energy
Detects speech vs silence Identifies voiced/unvoiced regions
Useful for endpoint detection
Q1(d) AMDF vs Autocorrelation
| AMDF | Autocorrelation |
|---|---|
| Computes absolute difference | Computes similarity |
| Minimum indicates pitch | Maximum indicates pitch |
| Lower computational load | More accurate |
Q1(e) Purpose of spectrographic displays Visualize frequency content over time
Identify formants, pitch, transitions Analyze speech dynamics
Q1(f) Properties of STFT
Time-frequency representation Based on windowing
Trade-off between time & frequency resolution Overlapping windows improve accuracy
Q1(g) Homomorphic vocoder
A system that separates source and vocal tract components using cepstral analysis.
Used in: speech coding, speech recognition, speaker identification.
Q1(h) Formant estimation using homomorphic methods
Compute log spectrum Apply inverse FFT → cepstrum
Separate low quefrency (vocal tract) Peaks correspond to formants
Q1(i) Prediction error in LPC
Difference between actual speech sample and predicted sample using past samples.
Q1(j) Significance of NMSE in LPC Measures prediction accuracy
Lower NMSE = better LPC model Used to evaluate LPC performance
SECTION B
(Attempt any three – 10 × 3 = 30 marks)
Q2(a) Speech production mechanism & acoustic phonetics
Speech is produced when airflow from lungs excites the vocal cords (source).
The vocal tract shapes the sound by resonance (filter).
Acoustic phonetics analyzes this sound in terms of spectral features, formants, pitch, and energy.
Q2(b) Short-time zero-crossing rate (ZCR)
ZCR counts how often signal crosses zero in a frame. High ZCR → unvoiced sounds
Low ZCR → voiced sounds Helps in speech/silence classification
Q2(c) Short-time Fourier analysis
Speech is non-stationary Divides signal into short frames
FFT applied on each frame Enables time-frequency analysis
Q2(d) Homomorphic processing – benefits & limitations
Benefits
Separates source & filter Robust spectral analysis
Limitations Computationally expensive
Phase unwrapping issues Less suitable for real-time systems
Q2(e) LPC & lossless tube model relationship
LPC models vocal tract as all-pole filter Tube model represents tract as concatenated tubes
LPC coefficients approximate tube resonances (formants)
SECTION C
(Attempt ONE from each question – 10 × 5 = 50 marks)
Q3(a) Acoustic theory of speech production
Speech is modeled as: Speech=Source×Vocal Tract×RadiationSpeech = Source × Vocal\ Tract × RadiationSpeech=Source×Vocal Tract×Radiation
Voiced → periodic excitation Unvoiced → noise excitation
Vocal tract acts as filter Foundation for LPC, vocoders, speech synthesis
Significance Simplifies speech modeling
Enables efficient speech coding Used in ASR & TTS systems
Q3(b) Lossless tube models Vocal tract modeled as uniform tubes
Each tube represents tract segment Reflection coefficients simulate articulator movement
Accurately models formant frequencies
Q4(a) Short-time energy & average magnitude
Short-time energy E(n)=∑∣x(n)∣2w(n)E(n)=\sum |x(n)|^2 w(n)E(n)=∑∣x(n)∣2w(n)
Average magnitude M(n)=∑∣x(n)∣w(n)M(n)=\sum |x(n)| w(n)M(n)=∑∣x(n)∣w(n)
Uses Endpoint detection
Speech activity detection Voiced/unvoiced analysis
Q4(b) Autocorrelation vs AMDF for pitch
| Parameter | Autocorrelation | AMDF |
|---|---|---|
| Accuracy | High | Moderate |
| Noise resistance | Good | Poor |
| Complexity | High | Low |
| Pitch detection | Robust | Faster |
Q5(a) Spectrographic displays Time on x-axis
Frequency on y-axis Intensity as color
Shows formants, pitch, harmonics Widely used in speech analysis & linguistics
Q5(b) FFT-based filter banks
Input signal → FFT Frequency bins grouped into bands
Each band acts as filter Efficient implementation for MFCC extraction
Q6(a) Complex cepstrum computation
Steps: Compute FFT
Take log magnitude + phase Unwrap phase
Apply inverse FFT Used to separate excitation and vocal tract.
Q6(b) Homomorphic system
A system where convolution becomes addition using logarithmic transformation.
Application: source-filter separation in speech.
Q7(a) Autocorrelation method in LPC
Steps: Frame blocking
Compute autocorrelation Apply Levinson-Durbin algorithm
Obtain LPC coefficients
Q7(b) Principles of linear predictive analysis
Current sample predicted from past samples Minimizes prediction error
Models vocal tract as all-pole filter Widely used in speech compression