Thumbnail
Access Restriction
Open

Author Heeman, Peter A. ♦ Loken-Kim, K. H.
Source CiteSeerX
Content type Text
File Format PDF
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Speech Repair ♦ Spontaneous Speech ♦ Correcting Speech Repair ♦ Speech Recognition ♦ Machine Training Technique ♦ Language Dependent Aspect ♦ Humanhuman Task-oriented Spoken Dialog ♦ Repeat Something ♦ Train Corpus ♦ Language Model ♦ Language Independent Aspect ♦ English Speech Repair ♦ Change Something ♦ Reparandum Ip Uh ♦ Japanese Corpus ♦ Annotated Corpus
Abstract One of the characteristics of spontaneous speech is the abundance of speech repairs, in which speakers go back and repeat or change something they have just said. In other work [7], we proposed a language model for speech recognition that can detect and correct speech repairs in English. In this paper, we show that this model works equally as well on a Japanese corpus of spontaneous speech. The structure of the model captures the language independent aspect of speech repairs, while machine training techniques on an annotated corpus learn the language dependent aspects. 1. INTRODUCTION One of the biggest challenges in recognizing and understanding spontaneous speech is dealing with speech repairs, where speakers go back and change or repeat something they have just said. The following illustrates an English speech repair from the Trains corpus [6], a corpus of humanhuman task-oriented spoken dialogs. Example 1 we'll pick up a tank of --- #z # reparandum " ip uh ---#z# et the t...
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study