First International Conference on Spoken Language Processing (ICSLP 90)

Kobe, Japan
November 18-22, 1990

The ETL Speech Database for Speech Analysis and Recognition Research

Kazuyo Tanaka, Satoru Hayamizu, Kozo Ohta

Electrotechnical Laboratory, Ibaraki, Japan

This paper describes a speech database developed for speech analysis and recognition research at ETL. Its system design concept, system configuration and phonetic labeling are presented as well as database statistics. The features of the system are 1) utterance text generation from a statistic-phonological view, and 2) fine acoustic-phonetic labeling by semiautomatic techniques. An acoustically compact segment called APSeg is adopted for the labeling of speech samples and acoustic-phonetic variations are represented by directed networks. Some sorted results of the labeling are shown for a real speech database of a phonemically balanced word set.

Full Paper

Bibliographic reference.  Tanaka, Kazuyo / Hayamizu, Satoru / Ohta, Kozo (1990): "The ETL speech database for speech analysis and recognition research", In ICSLP-1990, 1101-1104.