Toward an Understanding of the Role of Speech Recognition in Nonnative Speech Assessment. TOEFL iBT Research Report. TOEFL iBT-02. ETS RR-07-02

Autor/inn/en	Zechner, Klaus; Bejar, Isaac I.; Hemat, Ramin
Titel	Toward an Understanding of the Role of Speech Recognition in Nonnative Speech Assessment. TOEFL iBT Research Report. TOEFL iBT-02. ETS RR-07-02
Quelle	In: ETS Research Report Series, (2007), (88 Seiten)Infoseite zur Zeitschrift PDF als Volltext kostenfreie Datei Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	2330-8516
Schlagwörter	Role; Computer Assisted Testing; Language Proficiency; Oral Language; Classification; Regression (Statistics); Scoring; Speech Skills; Computer Software; English (Second Language); Language Tests; Second Language Learning; Prompting; Cues; Evaluators; Test Validity; Evaluation Methods; Courseware; Test Preparation; Accuracy; Interrater Reliability; Factor Analysis; Test of English as a Foreign Language + Suchen Sie Ihr Suchwort? Rollen; Language skill; Language skills; Sprachkompetenz; Oral interpretation; Mündlicher Sprachgebrauch; Classification system; Klassifikation; Klassifikationssystem; Regression; Regressionsanalyse; Bewertung; Mündliche Leistung; Sprachfertigkeit; English as second language; English; Second Language; Englisch als Zweitsprache; Language test; Sprachtest; Zweitsprachenerwerb; Benutzerführung; Stichwort; Testvalidität; Lernsoftware; Interrater-Reliabilität; Faktorenanalyse
Abstract	The increasing availability and performance of computer-based testing has prompted more research on the automatic assessment of language and speaking proficiency. In this investigation, we evaluated the feasibility of using an off-the-shelf speech-recognition system for scoring speaking prompts from the LanguEdge field test of 2002. We first established the level of agreement between two trained scorers. We then adapted a speech engine to the language backgrounds and proficiency ranges of the speakers and developed a classification and regression tree (CART) for each of five prompts based on features computed from the output of the speech recognizer. In a validation on held-out data, we found that while our features are not sufficiently comprehensive to adequately score these prompts, collectively these features appear to capture reliably some aspects of speaking proficiency. (As Provided).
Anmerkungen	Educational Testing Service. Rosedale Road, MS19-R Princeton, NJ 08541. Tel: 609-921-9000; Fax: 609-734-5410; e-mail: RDweb@ets.org; Web site: https://www.ets.org/research/policy_research_reports/ets
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2020/1/01