GENERATING PHONEME MODELS FOR FORMING PHONOLOGICAL CONCEPTS

Hiroaki Kojima, Kazuyo Tanaka, Satoru Hayamizu

Research output: Contribution to conferencePaperpeer-review

1 Citation (Scopus)

Abstract

The aim of this work is to improve speech recognition performance by forming "phonological concepts". In order to improve speech recognition performance, the phoneme models or phone models of the system need to satisfy following two properties: l)preciseness and 2)ro-bustness. These two properties usually trade off against each other in traditional stochastic models. In order to satisfy the both simultaneously, we propose to simulates situations of a human infant learning a language. We call this "phonological concept formation", which is a task of acquiring knowledge of phonological system from spoken word samples without using any transcriptions except for the identification of each word in a lexicon. This knowledge includes what is the set of the whole phonemes, how the acoustic phonetic features of each phoneme are described, and how they are appropriately discriminated. The basis of this idea is specifying essen-tial situations of speech communication instead of pro-viding all encompassing universal samples of a spoken language. Based on this framework, this paper discusses about the method for generating both precise and robust models.

Original languageEnglish
Pages1699-1702
Number of pages4
Publication statusPublished - 1994
Externally publishedYes
Event3rd International Conference on Spoken Language Processing, ICSLP 1994 - Yokohama, Japan
Duration: 1994 Sep 181994 Sep 22

Conference

Conference3rd International Conference on Spoken Language Processing, ICSLP 1994
Country/TerritoryJapan
CityYokohama
Period94/9/1894/9/22

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'GENERATING PHONEME MODELS FOR FORMING PHONOLOGICAL CONCEPTS'. Together they form a unique fingerprint.

Cite this