Zobrazeno 1 - 10
of 69
pro vyhledávání: '"Sharon Goldwater"'
In the first year of life, infants' speech perception becomes attuned to the sounds of their native language. This process of early phonetic learning has traditionally been framed as phonetic category acquisition. However, recent studies have hypothe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::289816c4b4c598d23ad6e5a3bd08d71b
https://doi.org/10.31234/osf.io/jmqtn
https://doi.org/10.31234/osf.io/jmqtn
Publikováno v:
ACM Transactions on Social Computing. 3:1-25
Emoji are widely used in computer-mediated communication to express concepts and emotions. Skin tone modifiers were added in 2015 with the hope of better representing user diversity, and, indeed, recent work has shown that these modifiers are especia
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ba9f6f78016939ee04b6dfcbd470a40c
https://doi.org/10.1145/3377479
https://doi.org/10.1145/3377479
Publikováno v:
Sanabria, R, Tang, H & Goldwater, S 2021, On the Difficulty of Segmenting Words with Attention . in Proceedings of the Second Workshop on Insights from Negative Results in NLP . pp. 67-73, Workshop on Insights from Negative Results in NLP 2021, Punta Cana, Dominican Republic, 10/11/21 . https://doi.org/10.18653/v1/2021.insights-1.11
Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition, attention
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::782010330994a1e47937b2ff04f67b24
https://hdl.handle.net/20.500.11820/8909ba20-20e6-4e40-8db4-999ee81aa48a
https://hdl.handle.net/20.500.11820/8909ba20-20e6-4e40-8db4-999ee81aa48a
Publikováno v:
Open Mind
Open Mind, 2021, 5, pp.113-131. ⟨10.1162/opmi_a_00046⟩
Feldman, N H, Goldwater, S, Dupoux, E & Schatz, T 2021, ' Do Infants Really Learn Phonetic Categories? ', Open Mind: Discoveries in Cognitive Science (Open Mind), vol. 5, pp. 113-131 . https://doi.org/10.1162/opmi_a_00046
Open Mind : Discoveries in Cognitive Science
Open Mind, MIT Press, 2021, 5, pp.113-131. ⟨10.1162/opmi_a_00046⟩
Open Mind, 2021, 5, pp.113-131. ⟨10.1162/opmi_a_00046⟩
Feldman, N H, Goldwater, S, Dupoux, E & Schatz, T 2021, ' Do Infants Really Learn Phonetic Categories? ', Open Mind: Discoveries in Cognitive Science (Open Mind), vol. 5, pp. 113-131 . https://doi.org/10.1162/opmi_a_00046
Open Mind : Discoveries in Cognitive Science
Open Mind, MIT Press, 2021, 5, pp.113-131. ⟨10.1162/opmi_a_00046⟩
Early changes in infants’ ability to perceive native and nonnative speech sound contrasts are typically attributed to their developing knowledge of phonetic categories. We critically examine this hypothesis and argue that there is little direct evi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eae67c4fc324206816543622d7a01576
https://hal.science/hal-03993333
https://hal.science/hal-03993333
Publikováno v:
Robertson, A, Magdy, W & Goldwater, S 2021, ' Black or White but Never Neutral: How Readers Perceive Identity from Yellow or Skin-toned Emoji ', Proceedings of the ACM on Human-Computer Interaction, vol. 5, no. CSCW2, pp. 1-23 . https://doi.org/10.1145/3476091
Research in sociology and linguistics shows that people use language not only to express their own identity but to understand the identity of others. Recent work established a connection between expression of identity and emoji usage on social media,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9bd10f72470ba573cd30af043d1b5943
http://arxiv.org/abs/2105.05887
http://arxiv.org/abs/2105.05887
Publikováno v:
Matusevych, Y, Kamper, H, Schatz, T, Feldman, N H & Goldwater, S 2021, A phonetic model of non-native spoken word processing . in Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume . pp. 1480-1490, 16th conference of the European Chapter of the Association for Computational Linguistics, Virtual Conference, 19/04/21 . < https://www.aclweb.org/anthology/2021.eacl-main.127 >
Scopus-Elsevier
EACL
Scopus-Elsevier
EACL
Non-native speakers show difficulties with spoken word processing. Many studies attribute these difficulties to imprecise phonological encoding of words in the lexical memory. We test an alternative hypothesis: that some of these difficulties can ari
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::da003ad63bfd199b56dd129c4e241085
https://www.pure.ed.ac.uk/ws/files/208726114/A_phonetic_model_MATUSEVYCH_DOA11012021_VOR_CC_BY.pdf
https://www.pure.ed.ac.uk/ws/files/208726114/A_phonetic_model_MATUSEVYCH_DOA11012021_VOR_CC_BY.pdf
Publikováno v:
Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology.
This work describes the Edinburgh submission to the SIGMORPHON 2021 Shared Task 2 on unsupervised morphological paradigm clustering. Given raw text input, the task was to assign each token to a cluster with other tokens from the same paradigm. We use
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e34780d40ec8327fcb69737617776376
https://doi.org/10.18653/v1/2021.sigmorphon-1.9
https://doi.org/10.18653/v1/2021.sigmorphon-1.9
Publikováno v:
ACL/IJCNLP (1)
Parsing spoken dialogue poses unique difficulties, including disfluencies and unmarked boundaries between sentence-like units. Previous work has shown that prosody can help with parsing disfluent speech (Tran et al. 2018), but has assumed that the in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::898dfdae154e3b7b0777b453aed17dde
Publikováno v:
Kamper, H, Matusevych, Y & Goldwater, S 2021, ' Improved acoustic word embeddings for zero-resource languages using multilingual transfer ', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 29, pp. 1107-1118 . https://doi.org/10.1109/TASLP.2021.3060805
Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. Such embeddings can form the basis for speech search, indexing and discovery systems when conventional speech recognition is not possible. In zero-reso
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bee06d8088c8992a99f8a0a0e3cee868
http://arxiv.org/abs/2006.02295
http://arxiv.org/abs/2006.02295
Publikováno v:
ICASSP
Bansal, S, Kamper, H, Lopez, A & Goldwater, S 2020, Cross-Lingual Topic Prediction for Speech Using Translations . in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . Institute of Electrical and Electronics Engineers (IEEE), pp. 8164-8168, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, 4/05/20 . https://doi.org/10.1109/ICASSP40776.2020.9054169
Bansal, S, Kamper, H, Lopez, A & Goldwater, S 2020, Cross-Lingual Topic Prediction for Speech Using Translations . in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . Institute of Electrical and Electronics Engineers (IEEE), pp. 8164-8168, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, 4/05/20 . https://doi.org/10.1109/ICASSP40776.2020.9054169
Given a large amount of unannotated speech in a low-resource language, can we classify the speech utterances by topic? We consider this question in the setting where a small amount of speech in the low-resource language is paired with text translatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cff6e6baabbdc91526efd27011818b09
https://doi.org/10.1109/icassp40776.2020.9054169
https://doi.org/10.1109/icassp40776.2020.9054169