1 |
How much does prosody help word segmentation? A simulation study on infant-directed speech
|
|
|
|
In: ISSN: 0010-0277 ; EISSN: 1873-7838 ; Cognition ; https://hal.archives-ouvertes.fr/hal-03498888 ; Cognition, Elsevier, 2022, 219, pp.104961. ⟨10.1016/j.cognition.2021.104961⟩ (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Does infant-directed speech help phonetic learning? A machine learning investigation
|
|
|
|
In: ISSN: 0364-0213 ; EISSN: 1551-6709 ; Cognitive Science ; https://hal.archives-ouvertes.fr/hal-03080098 ; Cognitive Science, Wiley, 2021, 45 (5), ⟨10.1111/cogs.12946⟩ (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Does Infant-Directed Speech Help Phonetic Learning? A Machine Learning Investigation
|
|
|
|
BASE
|
|
Show details
|
|
5 |
A Distributional Analysis of Laughter Across Turns and Utterances
|
|
|
|
In: Laughter and Other Non-Verbal Vocalisations Workshop: Proceedings (2020); Laughter and Other Non-Verbal Vocalisations Workshop 2020 (2020)
|
|
BASE
|
|
Show details
|
|
6 |
A Distributional Analysis of Laughter Across Turns and Utterances ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
An analysis of prosodic boundary detection in German and Austrian German read speech
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Nasal Consonant Discrimination in Infant- and Adult-Directed Speech
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Are Words Easier to Learn From Infant- Than Adult-Directed Speech? A Quantitative Corpus-Based Investigation
|
|
|
|
In: ISSN: 0364-0213 ; EISSN: 1551-6709 ; Cognitive Science ; https://hal.archives-ouvertes.fr/hal-01888701 ; Cognitive Science, Wiley, 2018, 42 (5), pp.1586 - 1617. ⟨10.1111/cogs.12616⟩ (2018)
|
|
BASE
|
|
Show details
|
|
10 |
Different Parts of the same Elephant: a Roadmap to Disentangle and Connect Different Perspectives of Prosodic Prominence
|
|
|
|
BASE
|
|
Show details
|
|
11 |
The Role of Prosody and Speech Register in Word Segmentation: A Computational Modelling Perspective
|
|
|
|
In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) ; https://hal.inria.fr/hal-01687451 ; Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Jul 2017, Vancouver, Canada. ⟨10.18653/v1/P17-2028⟩ (2017)
|
|
BASE
|
|
Show details
|
|
12 |
Are words easier to learn from infant- than adult-directed speech? A quantitative corpus-based investigation ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Different parts of the same elephant: a roadmap to disentangle and connect different perspectives on prosodic prominence
|
|
|
|
In: 18th International Congress of Phonetic Sciences ; https://halshs.archives-ouvertes.fr/halshs-01687856 ; 18th International Congress of Phonetic Sciences, 2015, Glasgow, United Kingdom (2015)
|
|
BASE
|
|
Show details
|
|
14 |
Is Syllable Stress Information Robust for ASR in Adverse Conditions?
|
|
|
|
In: International Conference on Speech Prosody ; https://hal.archives-ouvertes.fr/hal-01026423 ; International Conference on Speech Prosody, May 2014, Dublin, Ireland. pp.939-943 (2014)
|
|
BASE
|
|
Show details
|
|
15 |
Incorporating Prosodic Boundaries in Unsupervised Term Discovery
|
|
|
|
In: International conference on Speech Prosody ; https://hal.archives-ouvertes.fr/hal-01026421 ; International conference on Speech Prosody, May 2014, Dublin, Ireland. pp.207-211 (2014)
|
|
Abstract:
International audience ; We present a preliminary investigation on the usefulness of prosodic boundaries for unsupervised term discovery (UTD). Studies in language acquisition show that infants use prosodic boundaries to segment continuous speech into word-like units. We evaluate whether such a strategy could also help UTD algo- rithms. Running a previously published UTD algorithm (MODIS) on a corpus of prosodically annotated English broadcast news revealed that many discovered terms straddle prosodic boundaries. We then implemented two variants of this algorithm: one that discards straddling items and one that truncates them to the nearest boundary (either prosodic or pause marker). Both algorithms showed a better term matching F-score compared to the baseline and higher level prosodic boundaries were found to be better than lower level boundaries or pause markers. In addition, we observed that the truncation algorithm, but not the discard algorithm, increased word boundary F-score over the baseline.
|
|
Keyword:
[INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM]
|
|
URL: https://hal.archives-ouvertes.fr/hal-01026421
|
|
BASE
|
|
Hide details
|
|
16 |
Bridging the gap between speech technology and natural language processing: an evaluation toolbox for term discovery systems
|
|
|
|
In: Language Resources and Evaluation Conference ; https://hal.inria.fr/hal-01026368 ; Language Resources and Evaluation Conference, May 2014, Reykyavik, Iceland (2014)
|
|
BASE
|
|
Show details
|
|
17 |
Bridging the gap between speech technology and natural language processing : an evaluation toolbox for term discovery systems
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Using Broad Phonetic Classes to Guide Search in Automatic Speech Recognition
|
|
|
|
In: Interspeech ; INTERSPEECH - Annual Conference of the International Speech Communication Association ; https://hal.archives-ouvertes.fr/hal-00758427 ; INTERSPEECH - Annual Conference of the International Speech Communication Association, 2012, United States (2012)
|
|
BASE
|
|
Show details
|
|
19 |
Automatic Speech Segmentation for Italian (ASSI): tools, models, evaluation and applications
|
|
|
|
In: Convegno dell'Associazione Italiana Scienze della Voce 7 ; https://hal.archives-ouvertes.fr/hal-01514842 ; Convegno dell'Associazione Italiana Scienze della Voce 7, Jan 2011, Lecce, Italy. pp.8 (2011)
|
|
BASE
|
|
Show details
|
|
|
|