A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Filters
Combining the detection and correction of speech repairs
Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96
Preserved Fulltext
Previous approaches to detecting and correcting speech repairs have for the most part separated these two problems. ...
In this paper, we present a statistical model of speech repairs that uses information about the possible correction to help decide whether a speech repair actually occurred. ...
Rather, detection of speech repairs probably relies on the combination of a number clues, both acoustic and lexical. ...
doi:10.1109/icslp.1996.607129
fatcat:xytvuk6ghnduzbjv66lho7vrj4
Page 564 of Computational Linguistics Vol. 25, Issue 4
[page]
1999
Computational Linguistics
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
We also note that this work is the first proposal that combines the detection and correction of speech repairs, the identification of intonational phrases and discourse markers, and POS tag- ging, in a ...
Hence our comparison is with systems that address only part of the problem.
9.1 Speech Repairs
Table 15 gives the results of the full model for detecting and correcting speech re- pairs. ...
Integrating multiple knowledge sources for detection and correction of repairs in human-computer dialog
1992
Proceedings of the 30th annual meeting on Association for Computational Linguistics -
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We present here criteria and techniques for automatically detecting the presence of a repair, its location, and making the appropriate correction. ...
We have analyzed 607 sentences of spontaneous human-computer speech data containing repairs, drawn from a total corpus of 10,718 sentences. ...
We would also like to thank Robin Lickley for his feedback on the acoustics section, Elizabeth Wade for assistance with the statistics, and Mark Gawron for work on the Gemini grammar. ...
doi:10.3115/981967.981975
dblp:conf/acl/BearDS92
fatcat:5d3vgf6mmnelxbb6tl3hdwferu
Monitoring for speech errors has different functions in inner and overt speech
[chapter]
2010
Linguistics Today
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
It is expected that in inner speech, but not in overt speech, more nonword errors are detected than real-word ones, and that overt repairs of errors detected in inner speech differ from overt repairs of ...
errors detected in overt speech in that they have shorter offset-to-repair times, are spoken with raised instead of lowered intensity and pitch, and are less often accompanied by editing expressions. ...
In each individual interruption the lexicality was judged from the combination of speech error and repair. ...
doi:10.1075/la.150.09noo
fatcat:cnhmddxqbndklmgaxshr3w2qqi
Detecting and correcting speech repairs
1994
Proceedings of the 32nd annual meeting on Association for Computational Linguistics -
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
One of the most critical is the prevalence of speech repairs. This paper presents an algorithm that detects and corrects speech repairs based on finding the repair pattern. ...
In a fair test, our method, when combined with a statistical model to filter possible repairs, was successful at detecting and correcting 80% of the repairs, without using prosodic information or a parser ...
Funding gratefully received from the Natural Sciences and Engineering Research Council of Canada, from NSF under Grant IRI-90-13160, and from ONR/DARPA under Grant N00014-92-J-1512. ...
doi:10.3115/981732.981773
dblp:conf/acl/HeemanA94
fatcat:4uwqsr56lbhxdk2s67bjzirhsa
Detecting and Correcting Speech Repairs
[article]
1994
arXiv
pre-print
Preserved Fulltext
The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
Other Versions
One of the most critical is the prevalence of speech repairs. This paper presents an algorithm that detects and corrects speech repairs based on finding the repair pattern. ...
In a fair test, our method, when combined with a statistical model to filter possible repairs, was successful at detecting and correcting 80\% of the repairs, without using prosodic information or a parser ...
Funding gratefully received from the Natural Sciences and Engineering Research Council of Canada, from NSF under Grant IRI-90-13160, and from ONR/DARPA under Grant N00014-92-J-1512. ...
arXiv:cmp-lg/9406006v2
fatcat:gxxi7wefa5dxbccjcpazi5tdlm
Detection of errors during speech production: a review of speech monitoring models
2000
Cognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Finally, node structure theory views error detection as a natural out¯ow of the activation patterns in the node system for speech production. ...
The approaches differ on the points of consciousness, volition and control, the number of monitoring channels, and their speed, exibility, and capacity, and whether they can account for concurrent language ...
Also, I thank Loekie Elbers, Geert Panhuysen, and Frank Wijnen for their careful reading of a previous version of the text. ...
doi:10.1016/s0010-0277(00)00090-1
pmid:10986364
fatcat:e5de6hh4orafrivs3dyl6ysk5i
Processing Self-Corrections in a Speech-to-Speech System
[chapter]
2000
Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
We present a framework to detect and correct speech repairs where all relevant levels of information, i.e., acoustics, lexis, syntax and semantics can be integrated. ...
Speech repairs occur often in spontaneous spoken dialogues. The ability to detect and correct those repairs is necessary for any s p o k en language system. ...
He reports a recall rate of 81 and a precision of 83 for detection and 78 80 for correction. The test settings are nearly the same as test 2. ...
doi:10.1007/978-3-662-04230-4_10
fatcat:2kbpu2jtcbc3tkh6vvkhyqkmzy
A speech-first model for repair detection and correction
1993
Proceedings of the 31st annual meeting on Association for Computational Linguistics -
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We identify several cues based on acoustic and prosodic analysis of repairs in a corpus of spontaneous speech, and propose methods for exploiting these cues to detect and correct repairs. ...
However, while corpus studies have shown that about 10% of spontaneous utterances contain self-corrections, or RE-PAIRS, little is known about the extent to which cues in the speech signal may facilitate ...
CART analysis employed software written by Daryl Pregibon and Michael Riley. Speech analysis was done with Entropic Research Laboratory's WAVES software. ...
doi:10.3115/981574.981581
dblp:conf/acl/NakataniH93
fatcat:qmgkrhudzvb3ffxl6vfliiyjb4
Processing Self Corrections in a speech to speech system
[article]
2000
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We present a framework to detect and correct speech repairs where all relevant levels of information, i.e., acoustics, lexis, syntax and semantics can be integrated. ...
Speech repairs occur often in spontaneous spoken dialogues. The ability to detect and correct those repairs is necessary for any spoken language system. ...
He reports a recall rate of 81% and a precision of 83% for detection and 78%/80% for correction. The test settings are nearly the same as test 2. ...
arXiv:cs/0008016v1
fatcat:2w27bczyrfcxnbbbukdkjjb6se
Speech repair clues for detecting speech repairs in MICASE
2014
Discourse and Interaction
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The analysis shows the frequency of use of the individual speech repair clues such as editing term, word fragment and word correspondence. ...
Implementation of this algorithm into spontaneous speech is presented. Two types of speech repairs were analysed: modification and abridged repairs. ...
Here we show results on detection and correction of repairs by combining pattern matching with syntactic and semantic analysis. ...
doi:10.5817/di2014-2-5
fatcat:xhxzmcvkpnaatl6slq6xv42ou4
Intonational boundaries, speech repairs and discourse markers
1997
Proceedings of the 35th annual meeting on Association for Computational Linguistics -
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2006; you can also visit the original URL.
The file type is application/pdf.
To understand a speaker's turn of a conversation, one needs to segment it into intonational phrases, clean up any speech repairs that might have occurred, and identify discourse markers. ...
We put forward a statistical language model that resolves these problems, does POS tagging, and can be used as the language model of a speech recognizer. ...
Final preparation of this paper was done while the first author was visiting CNET, France Télécom. ...
doi:10.3115/976909.979650
dblp:conf/acl/HeemanA97
fatcat:hvsxpmtxfvc5ti32j25x5365uq
Intonational Boundaries, Speech Repairs and Discourse Markers: Modeling Spoken Dialog
[article]
1997
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
To understand a speaker's turn of a conversation, one needs to segment it into intonational phrases, clean up any speech repairs that might have occurred, and identify discourse markers. ...
We put forward a statistical language model that resolves these problems, does POS tagging, and can be used as the language model of a speech recognizer. ...
Final preparation of this paper was done while the first author was visiting CNET, France Télécom. ...
arXiv:cmp-lg/9704008v1
fatcat:y6qoqob23rdgtjpv55vbekamzy
Disfluency Detection Using a Bidirectional LSTM
2016
Interspeech 2016
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In experiments on the Switchboard corpus, the model achieves state-of-the-art performance for both the standard disfluency detection task and the correction detection task. ...
The BLSTM takes advantage of explicit repair states in addition to the standard reparandum states. ...
architecture and leverage the relatedness of repair and reparandum for repetition and correction disfluencies. ...
doi:10.21437/interspeech.2016-1247
dblp:conf/interspeech/ZayatsOH16
fatcat:f5c7axidgjd4zitbqgd3rbgxly
Speech Repairs, Intonational Boundaries and Discourse Markers: Modeling Speakers' Utterances in Spoken Dialog
[article]
1997
arXiv
pre-print
Preserved Fulltext
The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
detected and corrected. ...
The output of this language model is a much fuller account of the speaker's turn, with part-of-speech assigned to each word, intonation phrase endings and discourse markers identified, and speech repairs ...
markers, and detects and corrects speech repairs. ...
arXiv:cmp-lg/9712009v1
fatcat:c7jnyvlaczbolc2tq5gpzqgypq
« Previous
Showing results 1 — 15 out of 22,457 results