Multilingual Speech Evaluation: Case Studies on English, Malay and Tamil

Page view(s)
42
Checked on Aug 04, 2024
Multilingual Speech Evaluation: Case Studies on English, Malay and Tamil
Title:
Multilingual Speech Evaluation: Case Studies on English, Malay and Tamil
Journal Title:
Interspeech 2021
Keywords:
Publication Date:
03 September 2021
Citation:
Zhang, H., Shi, K., & Chen, N. F. (2021). Multilingual Speech Evaluation: Case Studies on English, Malay and Tamil. Interspeech 2021. doi:10.21437/interspeech.2021-1258
Abstract:
Speech evaluation is an essential component in computer-assisted language learning (CALL). While speech evaluation on English has been popular, automatic speech scoring on low resource languages remains challenging. Work in this area has focused on monolingual specific designs and handcrafted features stemming from resource-rich languages like English. Such approaches are often difficult to generalize to other languages, especially if we also want to consider suprasegmental qualities such as rhythm. In this work, we examine three different languages that possess distinct rhythm patterns: English (stress-timed), Malay (syllable-timed), and Tamil (mora-timed). We exploit robust feature representations inspired by music processing and vector representation learning. Empirical validations show consistent gains for all three languages when predicting pronunciation, rhythm and intonation performance.
License type:
Publisher Copyright
Funding Info:
There was no specific funding for the research done
Description:
https://www.isca-speech.org/archive/interspeech_2021/index.html
ISSN:
NA
Files uploaded:

File Size Format Action
zhang21fa-interspeech.pdf 348.56 KB PDF Open