Speech and Acoustic Information Processing

Course title

33011400

	MANO Kazunori
	TAKAHASHI Masanobu

Middle-level Diploma Policy (mDP)

Program / Major	mDP	Goals
IoT Course	DP-4a・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。
Software Course	DP-4b・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。
Media Course	DP-4c・2	キャリアを見据えた高度な専門知識画像や音響、サイバースペース等のメディア処理・デザイン技術を駆使し、社会的ニーズに適切に対応したシステムを開発できる。
Data Science Course	DP-4d・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。
Mechatronics Course	DP-4・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。
Architecture and Architectural Engineering Course	DP-4a・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。
Environmental Systems and Urban Planning Course	DP-4b・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。
Bioscience Course	DP-4a・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。
Biomedical Engineering Course	DP-4b・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。
Sports Engineering Course	DP-4c・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。
Mathematical Sciences Course	DP-4・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。

Purpose of class

The objective of this course is to learn the basic characteristics and technical fields related to speech and acoustics, and to acquire the knowledge necessary to perform works in these technical fields.
Classes are held on-demand.

Course description

Speech and Acoustics are fundamental means of information transfer in human communication and their technical applications are manifold. This lecture aims to provide basic knowledge of technical areas related to speech and acoustic processing, including basic characteristics of speech and acoustics, speech analysis techniques (correlation function, linear prediction, spectral analysis), noise and acoustic processing techniques (noise estimation and suppression, sound acquisition, transmission and reproduction), and pattern processing (feature extraction, classification, and identification of speech and acoustic information by machine learning). In addition, simple information processing exercises are performed for comprehension.

Goals and objectives

You can explain the physical and psychological characteristics and phenomena of speech and acoustics.
You can explain signal processing and information processing methods for speech and acoustics.
You can propose and explain applied services using speech and acoustics.

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

	Exercises (assignment report)	Practice (data processing)	Final Examination	Total.
1.	10%		20%	30%
2.	10%	20%	15%	45%
3.	10%		15%	25%
Total.	30%	20%	50%	-

Evaluation method and criteria

The total score of 60% or more is required to pass the course, consisting of 50% for exercises and practices, and 50% for the final examination.
Submitting all assignments and demonstrating a good understanding of the course content will be considered equivalent to a score of 80 points.

Language

Japanese

Class schedule

	Class schedule	HW assignments (Including preparation and review of the class.)	Amount of Time Required
1.	Class Guidance. What is Speech Acoustics? Introduction to Python programming.	Read syllabus and handouts.	60minutes
1.		Review and assignments.	120minutes
2.	Physical and psychological characteristics of speech and acoustics.	Read the handout.	70minutes
2.		Review and assignment.	120minutes
3.	Speech analysis (1): Correlation function and pitch extraction.	Read the handout.	70minutes
3.		Review and assignment.	120minutes
4.	Speech analysis (2): Spectral analysis	Practice (1): Programming and execution.	190minutes
5.	Speech analysis (3): Linear prediction	Read the handout.	70minutes
5.	Speech analysis (3): Linear prediction	Review and assignment.	120minutes
6.	Acoustic analysis (1): Noise estimation and suppression.	Read the handout.	70minutes
6.	Acoustic analysis (1): Noise estimation and suppression.	Review and assignment.	120minutes
7.	Acoustic analysis (2): Sound acquisition, transmission, and reproduction.	Read the handout.	70minutes
7.		Review and assignment.	120minutes
8.	Speech and audio coding (1): Speech coding, quantization, quality evaluation.	Read the handout.	70minutes
8.		Review and assignment.	120minutes
9.	Speech and audio coding (2): Audio coding and conversion techniques.	Read the handout.	70minutes
9.		Review and assignment.	120minutes
10.	Pattern processing of speech (1): Speech recognition.	Read the handout.	190minutes
10.	Pattern processing of speech (1): Speech recognition.	Review and assignment.
11.	Pattern processing of speech (2): Speech synthesis.	Practice (2): Programming and execution.	190minutes
12.	Speech and acoustic services (1): Dialogue system applications.	Read the handout.	70minutes
12.		Review and assignment.	120minutes
13.	Speech and acoustic services (2): Artificial reality, multimodal, and service applications.	Read the handout.	70minutes
13.		Review and assignment.	120minutes
14.	Final examination and overall summary.	Review and preparation for final examination.	190minutes
Total.	-	-	2650minutes

Feedback on exams, assignments, etc.

ways of feedback	specific contents about "Other"
Feedback outside of the class (ScombZ, mail, etc.)

Textbooks and reference materials

No textbook. Handout materials.

Prerequisites

Basic data processing programming skills (C, Python, etc.).

Office hours and How to contact professors for questions

Please contact us by e-mail.
Monday 5th period (17:00-18:40)

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

More than one class is interactive

Course by professor with work experience

Work experience	Work experience and relevance to the course content if applicable
Applicable	He has experience in research and development of media processing and recognition systems in a information and telecommunication company. He teaches technical terminologies and methods in relation to the systems and methods used in actual societies.

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 : Mon Mar 16 04:02:51 JST 2026