1993
DOI: 10.1006/csla.1993.1010
|View full text |Cite
|
Sign up to set email alerts
|

Parse scoring with prosodic information: an analysis/synthesis approach

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
24
0

Year Published

1997
1997
2003
2003

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 38 publications
(25 citation statements)
references
References 0 publications
1
24
0
Order By: Relevance
“…The LMs alone are already very good; we have, however, to consider that they cannot be (Kompe, 1997). Similar classi®cation experiments with syntactic±prosodic boundaries are reported in (Wang and Hirschberg, 1992;Ostendorf et al, 1993), where HMMs or classi®cation trees were used. The authors rely on perceptual±prosodic labels created on the basis of the ToBI system (Beckman and Ayers, 1994); for such labels, however, a much smaller amount of data can be obtained than in our case, cf.…”
Section: Automatic Classi®cation Of Boundariesmentioning
confidence: 97%
See 1 more Smart Citation
“…The LMs alone are already very good; we have, however, to consider that they cannot be (Kompe, 1997). Similar classi®cation experiments with syntactic±prosodic boundaries are reported in (Wang and Hirschberg, 1992;Ostendorf et al, 1993), where HMMs or classi®cation trees were used. The authors rely on perceptual±prosodic labels created on the basis of the ToBI system (Beckman and Ayers, 1994); for such labels, however, a much smaller amount of data can be obtained than in our case, cf.…”
Section: Automatic Classi®cation Of Boundariesmentioning
confidence: 97%
“…Our recognition rates are higher maybe because of the larger amount of training data; note, however, that the studies cannot be compared in a strict sense because they dier considerably w.r.t. several factors: the labelling systems are dierent, the numbers of classes dier, Wang and Hirschberg (1992) included the end of turns as label, Ostendorf et al (1993) used elicited, systematically ambiguous material that already because of that should be marked prosodically to a greater extent, and the languages dier.…”
Section: Automatic Classi®cation Of Boundariesmentioning
confidence: 99%
“…Recently more progress has been claimed in the relation between ASR performance and prosodic properties of utterances (e.g. Hirschberg et al, 2000;Litman et al, 2000;Hirschberg, 1999;Ostendorf et al, 1993;Shriberg et al, 1998). N€ o oth et al (1999) show that the integration of prosodic information might greatly improve the processing speed of the word search.…”
Section: Prosodic Features and Asrmentioning
confidence: 99%
“…In [7] prosodic information was used to score alternative parses of the same word sequence. Our approach di ers from that one, because we use the prosodic information in a preprocessing step where alternative string hypotheses are selected based on prosodic information and are parsed afterwards.…”
Section: Resultsmentioning
confidence: 99%