Automated Speaking Assessment: Using Language Technologies to Score Spontaneous Speech provides a thorough overview of state-of-the-art automated speech scoring technology as it is currently used at Educational Testing Service (ETS). Its main focus is related to the automated scoring of spontaneous speech elicited by TOEFL iBT Speaking section items, but other applications of speech scoring, such as for more predictable spoken responses or responses provided in a dialogic setting, are also discussed. The book begins with an in-depth overview of the nascent field of automated speech scoring—its history, applications, and challenges—followed by a discussion of psychometric considerations for automated speech scoring. The second and third parts discuss the integral main components of an automated speech scoring system as well as the different types of automatically generated measures extracted by the system features related to evaluate the speaking construct of communicative competence as measured defined by the TOEFL iBT Speaking assessment. Finally, the last part of the book touches on more recent developments, such as providing more detailed feedback on test takers’ spoken responses using speech features and scoring of dialogic speech. It concludes with a discussion, summary, and outlook on future developments in this area. Written with minimal technical details for the benefit of non-experts, this book is an ideal resource for graduate students in courses on Language Testing and Assessment as well as teachers and researchers in applied linguistics.
Table of Contents
Table of Contents
List of Contributors
Series Editors’ Foreword
List of Tables and Figures
Part I: Introduction
Chapter 1: Overview of Automated Speech Scoring
Keelan Evanini and Klaus Zechner
Chapter 2: Validity Considerations for Using Automated Scoring in Speaking Assessment
Mo Zhang, Brent Bridgeman, and Larry Davis
Chapter 3: Assessing Scoring Accuracy and Assessment Accuracy for Spoken Responses Using Human and Machine Scores
Mo Zhang, Lili Yao, Shelby J. Haberman, and Neil J. Dorans
Part II: Components of an Automated Speech Scoring System
Chapter 4: Automatic Speech Recognition for Automated Speech Scoring
Yao Qian, Patrick Lange, and Keelan Evanini
Chapter 5: Scoring and Filtering Models for Automated Speech Scoring
Anastassia Loukina and Su-Youn Yoon
Part III: Speech Features
Introduction to Part III
Chapter 6: Features Measuring Fluency and Pronunciation
Ching-Ni Hsieh, Klaus Zechner, and Xiaoming Xi
Chapter 7: Features Measuring Vocabulary and Grammar
Su-Youn Yoon, Xiaofei Lu, and Klaus Zechner
Chapter 8: Features Measuring Content and Discourse Coherence
Xinhao Wang and Keelan Evanini
Part IV: Recent Developments and Outlook
Chapter 9: Providing SpeechRater Feature Performance as Feedback on Spoken Responses
Lin Gu and Larry Davis
Chapter 10: Beyond Monologues: Automated Processing of Conversational Speech
Vikram Ramanarayanan, Keelan Evanini, and Eugene Tsuprun
Chapter 11: Summary and Outlook on Automated Speech Scoring
Klaus Zechner is a Senior Research Scientist at the Educational Testing Service and leads a team of speech scientists within the NLP & Speech group in the R&D division.
Keelan Evanini (Ph.D., University of Pennsylvania) is a Research Director at the Educational Testing Service.
"This book is a landmark volume that provide a comprehensive synthesis of work on automated speech assessment over the past 20 years at Educational Testing Services. The book compiles vital viewpoints, theories, applications, and knowledge from assessment specialists, linguists, computer scientists, and statisticians to provide an engaging and approachable introduction to a dense and innovative field of study that has direct and important implications for language assessment and natural language processing. The book will find a warm welcome in university classrooms, researchers’ bookshelves, and libraries for years to come by providing essential knowledge that will help new and experienced readers immerse themselves in automated speech assessment. The individual chapters provide important methodological advances, data analysis approaches, best-practice, and clear interpretations that will help move speech assessment into the next generation. The book fills an important gap by connecting automated speech technology, natural language processing, and statistical learning with applied speech assessment."
Scott Andrew Crossley, Georgia State University, USA.