This paper analyzes inter-labeler agreement of label choice and boundary placement for human phonetic transcriptions of continuous telephone speech in diierent languages. In experiment one, English, German, Mandarin and Spanish are labeled by uent speakers of the languages. In experiment two, German and Hindi are labeled by linguists who do not speak the languages. Experiment two uses a somewhat ner phonetic transcription set than experiment one. We compare the transcriptions of the utterances in terms of the minimum number of substitutions, insertions and deletions needed to map one transcription to the other. Native speakers agree on the average 67.52% of the time at the nest level of labeling, including diacritics. Non-native linguists agree 34.41% of the time. The implications of the results are discussed for evaluation of phonetic recognition algorithms.
[1]
Gary Tajchman,et al.
Effects of context and redundancy in the perception of naturally produced English vowels
,
1992,
ICSLP.
[2]
Ronald A. Cole,et al.
Perceptual studies on vowels excised from continuous speech
,
1992,
ICSLP.
[3]
Ronald A. Cole,et al.
The OGI multi-language telephone speech corpus
,
1992,
ICSLP.
[4]
Worldbet,et al.
ASCII Phonetic Symbols for the World s Languages Worldbet
,
1994
.