KA240001 Speech Recognition

Hiroshima University Syllabus

Japanese

Academic Year 2025Year School/Graduate School School of Informatics and Data Science

Lecture Code KA240001 Subject Classification Specialized Education

Subject Name 音声認識

Subject Name
（Katakana）オンセイニンシキ

Subject Name in
English Speech Recognition

Instructor YU YI

Instructor
(Katakana) ユ　イ

Campus Higashi-Hiroshima Semester/Term 3rd-Year, First Semester, Intensive

Days, Periods, and Classrooms (Int) Inte

Lesson Style Lecture Lesson Style
(More Details) Online (simultaneous interactive), Online (on-demand)

Lecture by using on demand video streams.
Moodle is used for mini-test and reports.

Credits 2.0 Class Hours/Week 　 Language of Instruction J : Japanese

Course Level 2 : Undergraduate Low-Intermediate

Course Area（Area） 25 : Science and Technology

Course Area（Discipline） 02 : Information Science

Eligible Students

Keywords

Special Subject for Teacher Education 　 Special Subject 　

Class Status
within Educational
Program
(Applicable only to targeted subjects for undergraduate students)
Criterion referenced
Evaluation
(Applicable only to targeted subjects for undergraduate students) Computer Science Program
（Knowledge and Understanding）
・D1. Knowledge and ability to understand the theoretical framework underlying computer science and to collect and process high-dimensional data through full use of information processing technology based on scientific logic.

Data Science Program
（Abilities and Skills）
・A. Information infrastructure development technology, information processing technology, technology that analyzes data and creates new added value.
・B. Ability to identify new problems independently and solve them through quantitative and logical thinking based on data, multifaceted perspectives, and advanced information processing and analysis.

Intelligence Science Program
（Abilities and Skills）
・B. Ability to identify new problems independently and solve them through quantitative and logical thinking based on data, multifaceted perspectives, and advanced information processing and analysis.
・D2. Information processing ability and data analysis ability to contribute to the application and development of artificial intelligence and IoT.

Class Objectives
/Class Outline In this course, students will learn the fundamental concepts of Automatic Speech Recognition (ASR) as well as the latest technologies, aiming to acquire the skills necessary to build and evaluate speech recognition systems. Specifically, the course will cover foundational knowledge of speech, learning Hidden Markov Models (HMMs), neural network-based acoustic models, and the implementation and application of speech recognition systems. The lectures will be conducted in a clear and accessible manner.

Class Schedule lesson1 Introduction to Speech Recognition
lesson2 Speech Analysis 1
lesson3 Speech Analysis 2
lesson4 Pattern Classification
lesson5 Hidden Markov Models
lesson6 Language Modeling
lesson7 Gaussian Mixture Models
lesson8 Neural Network Acoustic Models 1: Introduction
lesson9 Neural Network Acoustic Models 2: Hybrid HMM/DNN systems
lesson10 Neural Network Acoustic Models 3: DNN architectures
lesson11 Speaker Adaptation
lesson12 Discriminative Training
lesson13 Multilingual and Low-resource Speech Recognition
lesson14 End-to-End Systems
lesson15 Summary

Final examination and some reports

Text/Reference
Books,etc. No specific textbook.

PC or AV used in
Class,etc. Handouts, Microsoft Teams, Microsoft Stream, moodle

(More Details)

Learning techniques to be incorporated Quizzes/ Quiz format, Post-class Report

Suggestions on
Preparation and
Review Self-investigation of unknown words and/or interesting contents

Requirements

Grading Method Mini-tests: 40%, Final exam or report 60%

Practical Experience

Summary of Practical Experience and Class Contents based on it

Message

Other

Please fill in the class improvement questionnaire which is carried out on all classes.
Instructors will reflect on your feedback and utilize the information for improving their teaching.

Academic Year	2025Year	School/Graduate School	School of Informatics and Data Science
Lecture Code	KA240001	Subject Classification	Specialized Education
Subject Name	音声認識
Subject Name （Katakana）	オンセイニンシキ
Subject Name in English	Speech Recognition
Instructor	YU YI
Instructor (Katakana)	ユ　イ
Campus	Higashi-Hiroshima	Semester/Term	3rd-Year, First Semester, Intensive
Days, Periods, and Classrooms	(Int) Inte
Lesson Style	Lecture	Lesson Style (More Details)	Online (simultaneous interactive), Online (on-demand)
Lecture by using on demand video streams. Moodle is used for mini-test and reports.
Credits	2.0	Class Hours/Week		Language of Instruction	J : Japanese
Course Level	2 : Undergraduate Low-Intermediate
Course Area（Area）	25 : Science and Technology
Course Area（Discipline）	02 : Information Science
Eligible Students
Keywords
Special Subject for Teacher Education		Special Subject
Class Status within Educational Program (Applicable only to targeted subjects for undergraduate students)
Criterion referenced Evaluation (Applicable only to targeted subjects for undergraduate students)	Computer Science Program （Knowledge and Understanding）・D1. Knowledge and ability to understand the theoretical framework underlying computer science and to collect and process high-dimensional data through full use of information processing technology based on scientific logic. Data Science Program （Abilities and Skills）・A. Information infrastructure development technology, information processing technology, technology that analyzes data and creates new added value. ・B. Ability to identify new problems independently and solve them through quantitative and logical thinking based on data, multifaceted perspectives, and advanced information processing and analysis. Intelligence Science Program （Abilities and Skills）・B. Ability to identify new problems independently and solve them through quantitative and logical thinking based on data, multifaceted perspectives, and advanced information processing and analysis. ・D2. Information processing ability and data analysis ability to contribute to the application and development of artificial intelligence and IoT.
Class Objectives /Class Outline	In this course, students will learn the fundamental concepts of Automatic Speech Recognition (ASR) as well as the latest technologies, aiming to acquire the skills necessary to build and evaluate speech recognition systems. Specifically, the course will cover foundational knowledge of speech, learning Hidden Markov Models (HMMs), neural network-based acoustic models, and the implementation and application of speech recognition systems. The lectures will be conducted in a clear and accessible manner.
Class Schedule	lesson1 Introduction to Speech Recognition lesson2 Speech Analysis 1 lesson3 Speech Analysis 2 lesson4 Pattern Classification lesson5 Hidden Markov Models lesson6 Language Modeling lesson7 Gaussian Mixture Models lesson8 Neural Network Acoustic Models 1: Introduction lesson9 Neural Network Acoustic Models 2: Hybrid HMM/DNN systems lesson10 Neural Network Acoustic Models 3: DNN architectures lesson11 Speaker Adaptation lesson12 Discriminative Training lesson13 Multilingual and Low-resource Speech Recognition lesson14 End-to-End Systems lesson15 Summary Final examination and some reports
Text/Reference Books,etc.	No specific textbook.
PC or AV used in Class,etc.	Handouts, Microsoft Teams, Microsoft Stream, moodle
(More Details)
Learning techniques to be incorporated	Quizzes/ Quiz format, Post-class Report
Suggestions on Preparation and Review	Self-investigation of unknown words and/or interesting contents
Requirements
Grading Method	Mini-tests: 40%, Final exam or report 60%
Practical Experience
Summary of Practical Experience and Class Contents based on it
Message
Other
Please fill in the class improvement questionnaire which is carried out on all classes. Instructors will reflect on your feedback and utilize the information for improving their teaching.

Back to syllabus main page