733 Hits in 5.9 sec

Multistream Recognition of Dialogue Acts in Meetings [chapter]

Alfred Dielmann, Steve Renals
2006 Lecture Notes in Computer Science  
We propose a joint segmentation and classification approach for the dialogue act recognition task on natural multi-party meetings (ICSI Meeting Corpus).  ...  Prosodic features and a switching graphical model are used to estimate DA boundaries, in conjunction with a factored language model which is used to relate words and DA categories.  ...  Acknowledgment We thank Matthias Zimmermann and Elizabeth Shriberg for advice on broad DA categories.  ... 
doi:10.1007/11965152_16 fatcat:lre3bqiurjdljhkrupedbmluw4

Processing Units in Conversation: A Comparative Study of French and Mandarin Data

L. Prevot, S.-C. Tseng, K. Peshkov, A. C.-H. Chen
2015 Language and linguistics/Yuyan Ji Yuyangxue  
Speech segmentation into small units efficiently enhances a sensible and interpretable discourse structure.  ...  Unit completion location was identified by semantic structure (discourse unit), prosodic pattern (prosodic unit), and sequences of parts of speech (chunk).  ...  For deeper evaluation of the annotation of the whole CID corpus, please refer to Peshkov et al. (2012) , and for more on segmentation evaluation metrics applied to this kind of data see Peshkov & Prévot  ... 
doi:10.1177/1606822x14556605 fatcat:6ig5exgtozd6rd34uls3wpmqhm

Prosody in context: a review

Jennifer Cole
2014 Language, Cognition and Neuroscience  
Acoustic correlates of prosody cue this rich contextual information, but interpreting prosodic cues in terms of the lexical, syntactic, and discourse information they encode also requires recognizing prosodic  ...  perception that is robust to variation in prosodic form. when they occur at fixed locations in prosodic structure, such as the beginning or end of a prosodic word or phrase (Section 3).  ...  The beginning and end of a discourse (or rhetorical) segment are also, of course, the beginning and end of a prosodic phrase, but the discourse boundary is distinguished from a (discourse-medial) prosodic  ... 
doi:10.1080/23273798.2014.963130 fatcat:dreoglvbszcjpjpgawlvy4kfqq

Fusion Strategy for Prosodic and Lexical Representations of Word Importance

Sushant Kafle, Cecilia Ovesdotter Alm, Matt Huenerfauth
2019 Interspeech 2019  
We evaluate our fusion strategy on spoken dialogues and demonstrate performance increases over state-ofthe-art models.  ...  Starting from the assumption that acoustic-prosodic cues help identify important speech content, we investigate representation architectures that combine lexical and prosodic features and evaluate them  ...  Evaluation Metrics To compare the various models, we evaluated their predictions on word importance with the test set of the Word Importance corpus, described in Section 4.1.  ... 
doi:10.21437/interspeech.2019-1898 dblp:conf/interspeech/KafleAH19 fatcat:wvee7zzpkzbe7bodvydypatkni

PitchKeywordExtractor: Prosody-based Automatic Keyword Extraction for Speech Content

Yurij Lezhenin, Artyom Zhuikov, Natalia Bogach, Elena Boitsova, Evgeny Pyshkin
2017 Proceedings of the 2017 Federated Conference on Computer Science and Information Systems  
At the same time, some types of audio and audiovisual content, e. g. lectures, talks, interviews and other speech-oriented information, allow to perform keyword search by prosodic accents made by a speaker  ...  Existing keyword extraction techniques apply various text-based algorithms and metrics to locate the keywords.  ...  Our discussions and work together have greatly influenced this paper.  ... 
doi:10.15439/2017f326 dblp:conf/fedcsis/LezheninZBBP17 fatcat:irvj5zkkx5bwdp7z5mar5ebpyu


Heliana Mello, Lúcia Ferrari, Bruno Rocha
2020 Journal of Speech Sciences  
This link permits our joining multimodality, segmentation and prominence in speech as a topic for a scientific journal.  ...  Both speech and gestures require segmentation in order to be studied and understood scientifically, as knowing what the units of analysis are is crucial to the scientific endeavor.  ...  To close this JoSS issue, a study on the methodological steps for the automatic segmentation of speech intro prosodic units is presented.  ... 
doi:10.20396/joss.v9i00.14953 fatcat:kspvzss5vnc2jgkdhiuvxzbr3m

The Original ToBi System and the Evolution of the ToBi Framework [chapter]

Mary E. Beckman, Julia Hirschberg, Stefanie Shattuck-Hufnagel
2005 Prosodic Typology  
and prosodic unit boundaries to the audio and F0 signals.  ...  versus embedding of discourse segment purposes.  ...  It includes a powerful search engine that can find segments and events based on their sequential and hierarchical contexts.  ... 
doi:10.1093/acprof:oso/9780199249633.003.0002 fatcat:bloqhehhevfzbnwwjyh6ry6kle

New Methods for Prosodic Transcription: Capturing Variability as a Source of Information

Jennifer Cole, Stefanie Shattuck-Hufnagel
2016 Laboratory Phonology  
relate to the linguistic and discourse context, in the acoustic cues for those prosodic elements, and in the parameter values of the cues.  ...  The first is Rapid Prosody Transcription (RPT), which can be performed by non-experts using a simple set of unary labels to mark prominence and boundaries based on immediate auditory impression.  ...  Acknowledgements We have benefited from hearing many perspectives on prosodic transcription from participants at the first workshop on Advancing Prosodic Transcription in Stuttgart, 2012 and from the authors  ... 
doi:10.5334/labphon.29 fatcat:daojqdtysbbwbmelaanqlxh7wy

Multi-Resolution Language Grounding with Weak Supervision

R. Koncel-Kedziorski, Hannaneh Hajishirzi, Ali Farhadi
2014 Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)  
We define and optimize a factored objective function that allows us to leverage discourse structure and the compositional nature of both language and game events.  ...  We show that finer resolution grounding helps coarser resolution grounding, and vice versa.  ...  The authors also wish to thank Gina-Anne Levow, Yoav Artzi, Ben Hixon, and the anonymous reviewers for their valuable feedback on this work.  ... 
doi:10.3115/v1/d14-1043 dblp:conf/emnlp/Koncel-KedziorskiHF14 fatcat:bwhb3pk4qbeu7ai73rz4ujolzi

Automatic detection of prosodic boundaries in spontaneous speech

Tirza Biron, Daniel Baum, Dominik Freche, Nadav Matalon, Netanel Ehrmann, Eyal Weinreb, David Biron, Elisha Moses
2021 PLoS ONE  
We propose a method which does not require model training and utilizes two prosodic cues that are based on ASR output.  ...  Efforts to date have focused on detecting phrase boundaries using a variety of linguistic and acoustic cues.  ...  Lavner and J. Du Bois for their help. Author Contributions Conceptualization: Tirza Biron, Daniel Baum, Dominik Freche, Nadav Matalon, Elisha Moses.  ... 
doi:10.1371/journal.pone.0250969 pmid:33939754 pmcid:PMC8092678 fatcat:dncom2v77rbg5byddm7bttgmba

Linking bottom-up intonation stylization to discourse structure

Uwe D. Reichel
2014 Computer Speech and Language  
intonation contours from discourse structure defined by discourse segment boundaries and the information status of nouns within these segments.  ...  The predicted intonation contours were evaluated by human judgments of adequacy that yielded a high accordance.  ...  One way to address coherence consists in a linear discourse segmentation into subtopic units [30] .  ... 
doi:10.1016/j.csl.2014.03.005 fatcat:2jvrqorw5vcynkqjkjg564wroq

Communicative function and prosodic form in speech timing

Laurence White
2014 Speech Communication  
Here I propose a functional approach to prosodic speech timing, with particular reference to English.  ...  In the resulting framework, prosodic structure is held to influence speech timing directly only at the heads and edges of prosodic domains, through large, consistent lengthening effects.  ...  Evaluation of timing effects on the basis of their magnitude alone is additionally problematic because, given the manifold influences on segment duration, direct comparison between studies is near impossible  ... 
doi:10.1016/j.specom.2014.04.003 fatcat:z6q7uaqpurbddfovhyhcuhnfma

Inter-annotator agreement in spoken language annotation: Applying uα-family coefficients to discourse segmentation

Salvador Pons Bordería, Elena Pascual Aliaga
2021 Russian Journal of Linguistics  
This study applies IAA for the first time to the Valencia Espaol Coloquial (Val.Es.Co.) discourse segmentation model, designed for segmenting and labelling spoken language into discourse units.  ...  Three expert annotators segmented a spontaneous conversation into subacts, the minimal discursive unit of the Val.Es.Co. model, and labelled the resulting units according to a set of 10 subact categories  ...  The need for a new syntax (Narbona 1992) to account for spoken language set the grounds for an emerging area of research on models for discourse segmentation.  ... 
doi:10.22363/2687-0088-2021-25-2-478-506 fatcat:5sqlugf5xnbx5eijd4wxvyzxwa

Computational Induction of Prosodic Structure [article]

Dafydd Gibbon
2019 arXiv   pre-print
Second, a proposal is presented for an inductive grounding in the physical signal, in which prosodic structure is inferred using a language-independent method from the low-frequency spectrum of the speech  ...  hypothetico-deductive cycle by grounding in a language-independent inductive procedure of speech signal analysis.  ...  Summary and conclusion The present study completes the defective hypothetico-deductive cycle of mainstream linguistic studies of prosodic grammar by grounding the study of prosodic timing in a language-independent  ... 
arXiv:1912.07050v1 fatcat:jucvy6nw3bcjhbgsbcnhc3nehy

Deconstructing information structure

Angelika Kratzer, Elisabeth Selkirk
2020 Glossa  
A [G]-marked constituent signals a match with a discourse referent, whereas a [FoC]-marked constituent invokes alternatives and thereby signals a contrast.  ...  to discourse-related expressive meanings, and just happen to be spelled out prosodically in Standard American and British English.  ...  Funding Information This work was supported by NSF grants 0004038 and 1147083 to Elisabeth Selkirk and by a Radcliffe Fellowship and a Leverhulme Visiting Professorship at University College London for  ... 
doi:10.5334/gjgl.968 fatcat:mg7pnuf47zf5rgf5pxcgdv5waa
« Previous Showing results 1 — 15 out of 733 results