Automatic Rating of Spontaneous Speech for Low-Resource Languages

Ragheb Al-Ghezi, Yaroslav Getman, Ekaterina Voskoboinik, Mittul Singh, Mikko Kurimo

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

2 Citations (Scopus)

Abstract

Automatic spontaneous speaking assessment systems bring numerous advantages to second language (L2) learning and assessment such as promoting self-learning and reducing language teachers' workload. Conventionally, these systems are developed for languages with a large number of learners due to the abundance of training data, yet languages with fewer learners such as Finnish and Swedish remain at a disadvantage due to the scarcity of required training data. Nevertheless, recent advancements in self-supervised deep learning make it possible to develop automatic speech recognition systems with a reasonable amount of training data. In turn, this advancement makes it feasible to develop systems for automatically assessing spoken proficiency of learners of underresourced languages: L2 Finnish and Finland Swedish. Our work evaluates the overall performance of the L2 ASR systems as well as the the rating systems compared to human reference ratings for both languages.

Original languageEnglish
Title of host publication2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings
PublisherIEEE
Pages339-345
Number of pages7
ISBN (Electronic)979-8-3503-9690-4
DOIs
Publication statusPublished - 2023
MoE publication typeA4 Conference publication
EventIEEE Spoken Language Technology Workshop - Doha, Qatar
Duration: 9 Jan 202312 Jan 2023

Publication series

Name2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings

Conference

ConferenceIEEE Spoken Language Technology Workshop
Abbreviated titleSLT
Country/TerritoryQatar
CityDoha
Period09/01/202312/01/2023

Keywords

  • automatic speaking assessment
  • low-resource
  • Wav2Vec2

Fingerprint

Dive into the research topics of 'Automatic Rating of Spontaneous Speech for Low-Resource Languages'. Together they form a unique fingerprint.
  • DigiTala: Aka-Digi Tala

    Kurimo, M. (Principal investigator), Al-Ghezi, R. (Project Member), Getman, Y. (Project Member) & Voskoboinik, E. (Project Member)

    01/09/201931/08/2023

    Project: Academy of Finland: Other research funding

Cite this