EC-803 (C) RGPV B.Tech
Speech Processing (SP)
The official syllabus is free to read, no account needed.
Syllabus, notes and important questions for EC-803 (C)
- Syllabus Official RGPV syllabus Free
- Important Questions 1 set of questions Free
- Notes 5 documents Free
- Previous Year Papers None for EC-803 (C) yet
Syllabus units
Topics as the official RGPV syllabus lists them.
Unit 1 Basic Concepts of Speech Processing 6 topics
- Articulatory Phonetics – Production and Classification of Speech Sounds
- Acoustic Phonetics – acoustics of speech production
- Review of Digital Signal Processing concepts
- Short‑Time Fourier Transform (STFT)
- Filter‑Bank methods
- Linear Predictive Coding (LPC) methods
Unit 2 Speech Analysis 12 topics
- Speech distortion measures – mathematical and perceptual
- Log Spectral Distance
- Cepstral Distances
- Weighted Cepstral Distances
- Filtering
- Likelihood Distortions
- Spectral Distortion using a Warped Frequency Scale
- LPC coefficients
- PLP coefficients
- MFCC coefficients
- Dynamic Time Warping (DTW)
- Multiple Time‑Alignment Paths
Unit 3 Speech Modeling 5 topics
- Markov Processes
- Hidden Markov Model (HMM) evaluation
- Optimal State Sequence – Viterbi Search
- Baum‑Welch parameter re‑estimation
- Implementation issues of HMMs
Unit 4 Speech Recognition 5 topics
- Architecture of large‑vocabulary continuous speech recognition system
- Acoustic models
- Language models – n‑grams
- Context‑dependent sub‑word units
- Applications and present status
Unit 5 Speech Synthesis 5 topics
- Concatenative synthesis methods
- Waveform synthesis methods
- Sub‑word units for text‑to‑speech (TTS)
- Intelligibility and naturalness – role of prosody
- Applications and present status
Exam insights
Counted from 4 past EC-803 (C) papers.
Marks asked per paper, by unit
-
Unit 1 Basic Concepts of Speech Processing 8 marks
-
Unit 2 Speech Analysis 8 marks
-
Unit 3 Speech Modeling 6 marks
-
Unit 4 Speech Recognition 8 marks
-
Unit 5 Speech Synthesis 6 marks
Average marks of the questions from each unit in one paper. You answer only some of them, so the total is more than the paper’s maximum.
Asked again and again
-
Explain the principle of Linear Predictive Coding (LPC) and derive its autocorrelation equations.
Asked 4 times: 2022, 2023, 2024, 2025
-
Derive the formula for Mel‑frequency cepstral coefficients (MFCC) and compute them for a sample speech frame.
Asked 3 times: 2022, 2023, 2025
-
Draw and explain the block diagram of a Hidden Markov Model based speech recognizer.
Asked 3 times: 2022, 2023, 2024