Model-based automatic evaluation of L2 learner's English timing

Chatchawarn Hansakunbuntheung, Hiroaki Kato, Yoshinori Sagisaka

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    This paper proposes a method to automatically measure the timing characteristics of a second-language learner's speech as a means to evaluate language proficiency in speech production. We used the durational differences from native speakers' speech as an objective measure to evaluate the learner's timing characteristics. To provide flexible evaluation without the need to collect any additional English reference speech, we employed predicted segmental durations using a statistical duration model instead of measured raw durations of natives' speech. The proposed evaluation method was tested using English speech data uttered by Thai-native learners with different English-study experiences. An evaluation experiment shows that the proposed measure based on duration differences closely correlates to the subjects' English-study experiences. Moreover, segmental duration differences revealed Thai learners' speech-control characteristics in wordfinal stress assignment. These results support the effectiveness of the proposed model-based objective evaluation.

    Original languageEnglish
    Title of host publicationProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
    Pages2871-2874
    Number of pages4
    Publication statusPublished - 2009
    Event10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 - Brighton, United Kingdom
    Duration: 2009 Sep 62009 Sep 10

    Other

    Other10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009
    CountryUnited Kingdom
    CityBrighton
    Period09/9/609/9/10

    Fingerprint

    Population Groups
    Language
    Statistical Models
    Experiments

    Keywords

    • Quantitative evaluation
    • Second language
    • Speech timing

    ASJC Scopus subject areas

    • Human-Computer Interaction
    • Signal Processing
    • Software
    • Sensory Systems

    Cite this

    Hansakunbuntheung, C., Kato, H., & Sagisaka, Y. (2009). Model-based automatic evaluation of L2 learner's English timing. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (pp. 2871-2874)

    Model-based automatic evaluation of L2 learner's English timing. / Hansakunbuntheung, Chatchawarn; Kato, Hiroaki; Sagisaka, Yoshinori.

    Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2009. p. 2871-2874.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Hansakunbuntheung, C, Kato, H & Sagisaka, Y 2009, Model-based automatic evaluation of L2 learner's English timing. in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 2871-2874, 10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009, Brighton, United Kingdom, 09/9/6.
    Hansakunbuntheung C, Kato H, Sagisaka Y. Model-based automatic evaluation of L2 learner's English timing. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2009. p. 2871-2874
    Hansakunbuntheung, Chatchawarn ; Kato, Hiroaki ; Sagisaka, Yoshinori. / Model-based automatic evaluation of L2 learner's English timing. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2009. pp. 2871-2874
    @inproceedings{e7c80e6735c54320aee2896448fffa46,
    title = "Model-based automatic evaluation of L2 learner's English timing",
    abstract = "This paper proposes a method to automatically measure the timing characteristics of a second-language learner's speech as a means to evaluate language proficiency in speech production. We used the durational differences from native speakers' speech as an objective measure to evaluate the learner's timing characteristics. To provide flexible evaluation without the need to collect any additional English reference speech, we employed predicted segmental durations using a statistical duration model instead of measured raw durations of natives' speech. The proposed evaluation method was tested using English speech data uttered by Thai-native learners with different English-study experiences. An evaluation experiment shows that the proposed measure based on duration differences closely correlates to the subjects' English-study experiences. Moreover, segmental duration differences revealed Thai learners' speech-control characteristics in wordfinal stress assignment. These results support the effectiveness of the proposed model-based objective evaluation.",
    keywords = "Quantitative evaluation, Second language, Speech timing",
    author = "Chatchawarn Hansakunbuntheung and Hiroaki Kato and Yoshinori Sagisaka",
    year = "2009",
    language = "English",
    pages = "2871--2874",
    booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

    }

    TY - GEN

    T1 - Model-based automatic evaluation of L2 learner's English timing

    AU - Hansakunbuntheung, Chatchawarn

    AU - Kato, Hiroaki

    AU - Sagisaka, Yoshinori

    PY - 2009

    Y1 - 2009

    N2 - This paper proposes a method to automatically measure the timing characteristics of a second-language learner's speech as a means to evaluate language proficiency in speech production. We used the durational differences from native speakers' speech as an objective measure to evaluate the learner's timing characteristics. To provide flexible evaluation without the need to collect any additional English reference speech, we employed predicted segmental durations using a statistical duration model instead of measured raw durations of natives' speech. The proposed evaluation method was tested using English speech data uttered by Thai-native learners with different English-study experiences. An evaluation experiment shows that the proposed measure based on duration differences closely correlates to the subjects' English-study experiences. Moreover, segmental duration differences revealed Thai learners' speech-control characteristics in wordfinal stress assignment. These results support the effectiveness of the proposed model-based objective evaluation.

    AB - This paper proposes a method to automatically measure the timing characteristics of a second-language learner's speech as a means to evaluate language proficiency in speech production. We used the durational differences from native speakers' speech as an objective measure to evaluate the learner's timing characteristics. To provide flexible evaluation without the need to collect any additional English reference speech, we employed predicted segmental durations using a statistical duration model instead of measured raw durations of natives' speech. The proposed evaluation method was tested using English speech data uttered by Thai-native learners with different English-study experiences. An evaluation experiment shows that the proposed measure based on duration differences closely correlates to the subjects' English-study experiences. Moreover, segmental duration differences revealed Thai learners' speech-control characteristics in wordfinal stress assignment. These results support the effectiveness of the proposed model-based objective evaluation.

    KW - Quantitative evaluation

    KW - Second language

    KW - Speech timing

    UR - http://www.scopus.com/inward/record.url?scp=70450240918&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=70450240918&partnerID=8YFLogxK

    M3 - Conference contribution

    SP - 2871

    EP - 2874

    BT - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

    ER -