https://hal.archives-ouvertes.fr/hal-00499180/document

Automatic speech recognition and speech variability: A review

An overview of spoken language technology for education

We investigate the suitability of deploying speech technology in computer-based systems that can be used to teach foreign language skills. In reviewing the current state of speech recognition and speech processing technology and by examining a number of voice-interactive CALL applications, we suggest how to create robust interactive learning environments that exploit the strengths of speech technology while working around its limitations. In the conclusion, we draw on our review of these applications to identify directions of future research that might improve both the design and the overall performance of voice-interactive CALL systems.

https://scholarspace.manoa.hawaii.edu/bitstream/10125/25032/1/02_01_article3.pdf

Speech Technology in Computer-Assisted Language Learning: Strengths and Limitations of a New CALL Paradigm.

Improved mispronunciation detection with deep neural network trained acoustic models and transfer learning based logistic regression classifiers

Pronunciation, long on the periphery of applied linguistics research and pedagogy, continues to grow in importance because of its central roles in speech recognition, speech perception, and speaker identity. Pronunciation-related issues such as comprehensibility, accent, and the mutual intelligibility of varieties of world Englishes are central to many questions in applied linguistics. This calls for a sophisticated understanding of how technological tools that have long been used to shed light on phonological categories can be applied to teaching. Research into computer-assisted pronunciation teaching (CAPT) suggests that both researchers and pronunciation teachers increasingly make use of technology to answer key questions, to ensure that claims are defensible, and to develop theories and practices that more closely match acoustic reality. This article reviews three key areas where computer technology and pronunciation intersect: (1) appropriate pedagogical goals and the measurement of improvement; (2) the ability of CAPT to give useful, automatic feedback; and (3) the use of technology in diagnosing pronunciation errors. This article concludes with recommendations for key technological competencies needed by any researcher or teacher who examines pronunciation-related issues.

Computer technology in teaching and researching pronunciation

http://svr-www.eng.cam.ac.uk/~sjy/papers/wiyo00.pdf

Phone-level pronunciation scoring and assessment for interactive language learning

Use of speech recognition in computer-assisted language learning

This work presents methods of assessing non-native speech to aid computer-assisted pronunciation teaching. These methods are based on automatic speech recognition (ASR) techniques using Hidden Markov Models. Conn-dence scores at the phoneme level are calculated to provide detailed information about the pronunciation quality of a foreign language student. Experimental results are given based on both artiicial data and a database of non-native speech, the latter being recorded speciically for this purpose. The presented results demonstrate the metrics' capability to locate and assess mispronunciations at the phoneme level.

Language learning based on non-native speech recognition

Computer-assisted pronunciation teaching based on automatic speech recognition

This paper introduces a family of three techniques to improve non-native speaker-independent recognition if the type of accent, i.e. the mother tongue of a non-native speaker is known. These techniques permit the computation of non-native models without requiring adaptation data, that is, they can be computed o -line. The improved recognition performance of these approaches is obtained by combining speaker-independent hidden Markov models of the target language, i.e. the language to be taught, and of the source language, i.e. the speaker's native language. All three combination techniques require a mapping between the two languages to de ne which source model state combines with each target model state. A method has been developed to derive such a mapping automatically. Recognition results are given for all three techniques applied to the two cases of Spanish accented British English and Japanese accented British English. The average baseline word error rate of 28:3% can be decreased to 22:9% for the rst method, to 24:1% for the second and to 20:6% for the last method, which equals a relative improvement of 29% without adaptation.

Silke M. Witt

Papers

Phone-level pronunciation scoring and assessment for interactive language learning

Use of speech recognition in computer-assisted language learning

Language learning based on non-native speech recognition

Computer-assisted pronunciation teaching based on automatic speech recognition

Off-line acoustic modelling of non-native accents