Evaluation of aspiration problems in L2 English pronunciation employing machine learning
Authors:
- 1 July 2021
- journal article
- conference paper
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 150 (1) , 120-132
Abstract
The approach proposed in this study includes methods specifically dedicated to the detection of allophonic variation in English. This study aims to find an efficient method for automatic evaluation of aspiration in the case of Polish second-language (L2) English speakers' pronunciation when whole words are analyzed instead of particular allophones extracted from words. Sample words including aspirated and unaspirated allophones were prepared by experts in English phonetics and phonology. The datasets created include recordings of words pronounced by nine native English speakers of standard southern British accent and 20 Polish L2 English users. Complete unedited words are treated as input data for feature extraction and classification algorithms such as k-nearest neighbors, naive Bayes method, long-short term memory, and convolutional neural network (CNN). Various signal representations, including low-level audio features, the so-called mid-term and feature trajectory, and spectrograms, are tested in the context of their usability for the detection of aspiration. The results obtained show high potential for an automated evaluation of pronunciation focused on a particular phonological feature (aspiration) when classifiers analyze whole words. Additionally, CNN returns satisfying results for the automated classification of words containing aspirated and unaspirated allophones produced by Polish L2 speakers.Keywords
Funding Information
- Narodowe Centrum Nauki (Dec. No. 2015/17/B/ST6/01874)
This publication has 38 references indexed in Scilit:
- Deep Belief Neural Networks and Bidirectional Long-Short Term Memory Hybrid for Speech RecognitionArchives of Acoustics, 2015
- A cross-language acoustic study of initial and final allophones of /l/Speech Communication, 2012
- Automatic recognition of regional phonological variation in conversational interactionSpeech Communication, 2010
- A new method for mispronunciation detection using Support Vector Machine based on Pronunciation Space ModelsSpeech Communication, 2009
- Place of articulation and first formant transition pattern both affect perception of voicing in EnglishJournal of Phonetics, 2001
- Variation and universals in VOT: evidence from 18 languagesJournal of Phonetics, 1999
- Bandwidth Selection for Kernel Density EstimationThe Annals of Statistics, 1991
- A cross-language study of range of voice onset time in the perception of initial stop voicingThe Journal of the Acoustical Society of America, 1981
- The perception of voice onset time in PolishThe Journal of the Acoustical Society of America, 1978
- The Hyphen as a Phonetic SignSTUF - Language Typology and Universals, 1956