Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Matthew Snover"'
Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute -- conversationa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f9f33d8a245d6b721f4c8b8a83d731e8
http://arxiv.org/abs/2110.15836
http://arxiv.org/abs/2110.15836
Publikováno v:
ICASSP
Automatic speech recognition (ASR) systems are highly sensitive to train-test domain mismatch. However, because transcription is often prohibitively expensive, it is important to be able to make use of available transcribed out-of-domain data. We add
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1e7d6f71b2a9245a530e6ef691f5399a
https://doi.org/10.1109/icassp39728.2021.9413869
https://doi.org/10.1109/icassp39728.2021.9413869
Publikováno v:
ICASSP
We present an importance sampling based approach to the active learning problem of selecting additional training data to supplement a seed model. Our proposed Δ-AUC selection optimizes AUC improvement in keyword search and is evaluated on the Spanis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ae713a9c848a4aec14a8784b9ac55aa6
https://doi.org/10.1109/icassp.2016.7472076
https://doi.org/10.1109/icassp.2016.7472076
Publikováno v:
Machine Translation. 23:169-179
Recent efforts to develop new machine translation evaluation methods have tried to account for allowable wording differences either in terms of syntactic structure or synonyms/paraphrases. This paper primarily considers syntactic structure, combining
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::54f97acfffb37ec66790841771c07d68
https://doi.org/10.1007/s10590-009-9057-6
https://doi.org/10.1007/s10590-009-9057-6
Publikováno v:
Machine Translation. 23:117-127
This paper describes a new evaluation metric, TER-Plus (TERp) for automatic evaluation of machine translation (MT). TERp is an extension of Translation Edit Rate (TER). It builds on the success of TER as an evaluation metric and alignment tool and ad
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::41c1932530fdf9af3231033ec3744f06
https://doi.org/10.1007/s10590-009-9062-9
https://doi.org/10.1007/s10590-009-9062-9
Publikováno v:
WMT@EACL
Automatic Machine Translation (MT) evaluation metrics have traditionally been evaluated by the correlation of the scores they assign to MT output with human judgments of translation performance. Different types of human judgments, such as Fluency, Ad
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1a9b09380d60ec5a7310a9b069085631
https://doi.org/10.3115/1626431.1626480
https://doi.org/10.3115/1626431.1626480
Publikováno v:
EMNLP
Traditionally, statistical machine translation systems have relied on parallel bi-lingual data to train a translation model. While bi-lingual parallel data are expensive to generate, monolingual data are relatively common. Yet monolingual data have b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f8c3d8560b3dcc43df61a9c06020ef94
https://doi.org/10.3115/1613715.1613825
https://doi.org/10.3115/1613715.1613825
Autor:
Matthew Lease, Bonnie J. Dorr, Mary P. Harper, L. Yung, Brian Roark, Yang Liu, John Hale, Matthew Snover, Anna Krasnyanskaya, Robin Stewart, Izhak Shafran
Publikováno v:
ICASSP (1)
We present a reranking approach to sentence-like unit (SU) boundary detection, one of the EARS metadata extraction tasks. Techniques for generating relatively small n-best lists with high oracle accuracy are presented. For each candidate, features ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::44f40121d2f0fe7b303b43c9ea27b6f6
https://doi.org/10.1109/icassp.2006.1660078
https://doi.org/10.1109/icassp.2006.1660078
Autor:
Yang Liu, Izhak Shafran, Anna Krasnyanskaya, Brian Roark, John Hale, L. Yung, Matthew Snover, Bonnie J. Dorr, Mary P. Harper, Matthew Lease, Robin Stewart
Publikováno v:
ACL
A grammatical method of combining two kinds of speech repair cues is presented. One cue, prosodic disjuncture, is detected by a decision tree-based ensemble classifier that uses acoustic cues to identify where normal prosody seems to be interrupted (
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9161fa2e22a31d0ad0b93c4ff5e11bc3
https://doi.org/10.3115/1220175.1220196
https://doi.org/10.3115/1220175.1220196
Publikováno v:
HLT-NAACL (Short Papers)
This paper describes a transformation-based learning approach to disfluency detection in speech transcripts using primarily lexical features. Our method produces comparable results to two other systems that make heavy use of prosodic features, thus d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::acaf63ffb00293cf9a082c210b8bfa7b
https://doi.org/10.3115/1613984.1614024
https://doi.org/10.3115/1613984.1614024