COURSE INFORMATION Course Title: SPEECH PROCESSING

Code	Course Type	Regular Semester	Theory	Practice	Lab	Credits	ECTS
CEN 851	C	99	3	2	0	4	7.5

Academic staff member responsible for the design of the course syllabus (name, surname, academic title/scientific degree, email address and signature)	NA
Lecturer (name, surname, academic title/scientific degree, email address and signature) and Office Hours:	Julian Hoxha
Second Lecturer(s) (name, surname, academic title/scientific degree, email address and signature) and Office Hours:	NA
Teaching Assistant(s) and Office Hours:	NA
Language:	English
Compulsory/Elective:	Elective
Classroom and Meeting Time:
Course Description:	-
Course Objectives:	The main goals of the subject is to present specific features of speech signals either in frequency or temporal domain and the basic techniques used in the processing of speech signals.

COURSE OUTLINE

Week	Topics
1	Introduction to Speech processing and applications of speech processing techniques.
2	Properties of speech signals in temporal and frequency domains.
3	Basic speech feature extraction methods.
4	Linear model of speech production, LPC analysis.
5	Pattern Comparison Techniques.
6	Speech distortion measures – mathematical and perceptual – Log Spectral Distance, Cepstral Distances, Weighted Cepstral Distances and Filtering, Likelihood Distortions, Spectral Distortion using a Warped Frequency Scale, LPC, PLP and MFCC Coefficients, Time Alignment and Normalization – Dynamic Time Warping, Multiple Time – Alignment Paths.
7	Bank of filters and psychoacoustic frequency scales.
8	Speech Modeling: Hidden Markov Models.
9	Vector quantization.
10	Speech recognition: dynamic programming, DTW algorithm.
11	Speech recognition: Discrete Hidden Markov models and Continuous Hidden Markov models.
12	Basic principles of speech synthesis.
13	Text-to-Speech Synthesis: Concatenative and waveform synthesis methods.
14	Subword units for TTS, intelligibility and naturalness – role of prosody, Applications and present status.

Prerequisite(s):	Signals & Systems, Digital Signal Processing, Fundamental of Probability and Random Process.
Textbook:	J. Flanagan, J. Allen, and M. Hasagawa-Johnson, Speech Analysis Synthesis and Perception, 3rd ed., 2008.
Other References:
Laboratory Work:
Computer Usage:
Others:	No

COURSE LEARNING OUTCOMES

1	Explain specific features of speech signals either in frequency or temporal domain.
2	Explain basic techniques used in the processing of speech signals such as parameterization of speech signals for its analyses i.e. MFCC, LPC, filter bank, energy, zero crossing, AMDF, autocorrelation, etc.
3	Modeling and classification techniques for speech detection, speaker identification and speech recognition i.e. vector quantization, GMM, DTW, discrete HMM, continuous HMM, etc.
4	Basic principles of speech synthesis and compression.

COURSE CONTRIBUTION TO... PROGRAM COMPETENCIES (Blank : no contribution, 1: least contribution ... 5: highest contribution)

No	Program Competencies	Cont.
Doctorate (PhD) in Computer Engineering Program
1	Engineering graduates with sufficient theoretical and practical background for a successful profession and with application skills of fundamental scientific knowledge in the engineering practice.	5
2	Engineering graduates with skills and professional background in describing, formulating, modeling and analyzing the engineering problem, with a consideration for appropriate analytical solutions in all necessary situations	5
3	Engineering graduates with the necessary technical, academic and practical knowledge and application confidence in the design and assessment of machines or mechanical systems or industrial processes with considerations of productivity, feasibility and environmental and social aspects.	5
4	Engineering graduates with the practice of selecting and using appropriate technical and engineering tools in engineering problems, and ability of effective usage of information science technologies.	4
5	Ability of designing and conducting experiments, conduction data acquisition and analysis and making conclusions.	4
6	Ability of identifying the potential resources for information or knowledge regarding a given engineering issue.	4
7	The abilities and performance to participate multi-disciplinary groups together with the effective oral and official communication skills and personal confidence.	3
8	Ability for effective oral and official communication skills in foreign language.	3
9	Engineering graduates with motivation to life-long learning and having known significance of continuous education beyond undergraduate studies for science and technology.	2
10	Engineering graduates with well-structured responsibilities in profession and ethics.	1
11	Engineering graduates who are aware of the importance of safety and healthiness in the project management, workshop environment as well as related legal issues.	1
12	Consciousness for the results and effects of engineering solutions on the society and universe, awareness for the developmental considerations with contemporary problems of humanity.	1

COURSE EVALUATION METHOD

Method	Quantity	Percentage
Midterm Exam(s)	1	30
Project	1	30
Final Exam	1	40
	Total Percent:	100%

ECTS (ALLOCATED BASED ON STUDENT WORKLOAD)

Activities	Quantity	Duration(Hours)	Total Workload(Hours)
Course Duration (Including the exam week: 16x Total course hours)	16	5	80
Hours for off-the-classroom study (Pre-study, practice)	5	3.5	17.5
Mid-terms	1	30	30
Assignments	1	30	30
Final examination	1	30	30
Other			0
Total Work Load:			187.5
Total Work Load/25(h):			7.5
ECTS Credit of the Course:			7.5