First European Conference on Speech Communication and Technology

Paris, France
September 27-29, 1989

Automatic Evaluation of English Pronunciation Based on Speech Recognition Techniques

Hiroshi Hamada, Satoshi Miki, Ryohei Nakatsu

NTT Human Interface Laboratories, Yokosuka, Kanagawa, Japan

A new method is proposed for automatically evaluating the English pronunciation quality of Japanese speakers. It is assumed that this can be determined based on three criteria: the static characteristics of phonetic spectra, the dynamic structure of spectrum sequences, and the prosodic characteristics of utterances. Evaluation is carried out by comparing English words pronounced by a Japanese with those pronounced by a native speaker using speech recognition techniques. Preliminary experiments show the evaluation results obtained using the proposed method to correspond well with human judgement of pronunciation quality.

Full Paper

Bibliographic reference.  Hamada, Hiroshi / Miki, Satoshi / Nakatsu, Ryohei (1989): "Automatic evaluation of English pronunciation based on speech recognition techniques", In EUROSPEECH-1989, 1421-1424.