Speech Processing

Course title

6M006700

Speech Processing

Click to show questionnaire result at 2017

Course content

Recently, speech processing is becoming more and more complex to provide high quality communication services. Speech processing, coding, and machine learning techniques are essential to obtain sufficient results.

Purpose of class

Students learn basic speech processing technology for modeling, prediction, estimation, and coding with machine learning.
Several data processing exercises with computer programming are also required.
In addition, each student will conduct a presentation and discussion on topics related to speech processing and related areas.

Goals and objectives

You can explain the theoretical knowledge of speech processing.
You can solve practical speech data processing in computer simulation exercises.
You can explain applications and services for speech processing.

Relationship between 'Goals and Objectives' and 'Course Outcomes'

	Reports and discussions of the assignments	Presentations	Total.
1.	40%		40%
2.	40%		40%
3.		20%	20%
Total.	80%	20%	-

Language

English

Class schedule

	Class schedule	HW assignments (Including preparation and review of the class.)	Amount of Time Required
1．	Introduction to speech processing and machine learning.	Read the syllabus.	180minutes
1．	Introduction to speech processing and machine learning.	Review the topics and do assignments
2．	Statistics and probability theory for speech processing	Read provided materials	70minutes
2．	Statistics and probability theory for speech processing	Review the topics and do assignments	120minutes
3．	Signal processing (1) : filter, and spectral analysis	Read provided materials	70minutes
3．	Signal processing (1) : filter, and spectral analysis	Review the topics and do assignments	120minutes
4．	Signal processing (2): linear prediction	Read provided materials	70minutes
4．	Signal processing (2): linear prediction	Review the topics and do assignments	120minutes
5．	Quantization and coding of speech (1)	Read provided materials	70minutes
5．	Quantization and coding of speech (1)	Review the topics and do assignments	120minutes
6．	Quantization and coding of speech (2)	Read provided materials	70minutes
6．	Quantization and coding of speech (2)	Review the topics and do assignments	120minutes
7．	Pattern recognition	Read provided materials	70minutes
7．	Pattern recognition	Review the topics and do assignments	120minutes
8．	Machine learning (1): Maximum likelihood estimation	Read provided materials	70minutes
8．	Machine learning (1): Maximum likelihood estimation	Review the topics and do assignments	120minutes
9．	Machine learning (2): Bayesian estimation	Read provided materials	70minutes
9．	Machine learning (2): Bayesian estimation	Review the topics and do assignments	120minutes
10．	Machine learning (3): Deep learning 1	Read provided materials	70minutes
10．	Machine learning (3): Deep learning 1	Review the topics and do assignments	120minutes
11．	Machine learning (4): Deep learning 2	Read provided materials	70minutes
11．	Machine learning (4): Deep learning 2	Review the topics and do assignments	120minutes
12．	Application of speech communications (1)	Read provided materials	70minutes
12．	Application of speech communications (1)	Review the topics and do assignments	120minutes
13．	Application of speech communications (2)	Read provided materials	70minutes
13．	Application of speech communications (2)	Review the topics and do assignments	120minutes
14．	Final presentation and discussion	Preparation for the presentation.	190minutes
Total.	-	-	2650minutes

Evaluation method and criteria

Assessment Criteria:
Reports and discussions in regular classes: 80% (Reports are assigned in every class.)
Presentations and discussions in the final class: 20% (Each student will give a presentation.)
For a total possible score of 100 points.

Passing Grade:
A total score of 60 points or higher is required to pass this class. If all assigned reports are submitted and discussed in regular classes and you present your report and answer questions in the final class, your score will be evaluated as 60 points or higher.

Feedback on exams, assignments, etc.

ways of feedback	specific contents about "Other"
Feedback in the class

Textbooks and reference materials

References:
Rabiner and Schafer, Theory and applications of digital speech processing, 2011.
C. Bishop, Pattern recognition and machine learning, 2006.
Other references are presented at each class.

Prerequisites

Basic knowledge of signal processing (Fourier transform, filter, Z-transform, etc.) and statistics and probability theory.
Computer programming skills (either Python, MATLAB, C/C++, or R ... ) for signal processing.

Office hours and How to contact professors for questions

Tuesday, 5th period (17:00-18:40)
Any reasonable times with prior appointments.
E-mail: mano[at]shibaura-it.ac.jp (Please replace [at] with @.)

Regionally-oriented

Non-regionally-oriented course

Development of social and professional independence

Course that cultivates an ability for utilizing knowledge
Course that cultivates a basic problem-solving skills

Active-learning course

About half of the classes are interactive

Course by professor with work experience

Work experience	Work experience and relevance to the course content if applicable
Applicable	Real appliations and data processing examples are explained based on the Professor's experiences in his ICT company, especially speech processing and communication systems development experiences.

Education related SDGs:the Sustainable Development Goals

4.QUALITY EDUCATION
8.DECENT WORK AND ECONOMIC GROWTH
9.INDUSTRY, INNOVATION AND INFRASTRUCTURE
12.RESPONSIBLE CONSUMPTION & PRODUCTION

Last modified : Fri Mar 14 04:09:41 JST 2025