2,727 Hits in 11.6 sec

High-quality speech-to-speech translation for computer-aided language learning

Chao Wang, Stephanie Seneff
2006 ACM Transactions on Speech and Language Processing  
The best speech translation performance (89.9% correct, 6.1% incorrect, and 4.0% rejected), is achieved by a system which combines the formal and example-based methods, using parsability by a domain-specific  ...  Translation quality was manually evaluated on a test set of 695 spontaneous utterances.  ...  ACKNOWLEDGMENTS The authors would like to thank Dr. Philipp Koehn for his generous help with the Pharaoh decoder for phrase-based statistical machine translation models.  ... 
doi:10.1145/1149290.1149291 dblp:journals/tslp/WangS06 fatcat:iue2g5sjafedfnwrudpctkyel4

Emotion sensitive speech control for human-robot interaction in minimal invasive surgery

Bjorn Schuller, Gerhard Rigoll, Salman Can, Hubertus Feussner
2008 RO-MAN 2008 - The 17th IEEE International Symposium on Robot and Human Interactive Communication  
We therefore introduce a robotdriven camera that can be controlled either manually by a joystick, or by speech to ensure free hands and feet, and reduced cognitive workload of the surgeon.  ...  In this work we therefore discuss the recording of a 3,035 turns database of spontaneous emotional speech in real life surgical operations.  ...  The authors gratefully acknowledge the contribution of the student researchers Jin Yao, Martin Polsky, and Thomas Mikschl.  ... 
doi:10.1109/roman.2008.4600708 dblp:conf/ro-man/SchullerRCF08 fatcat:r34pcoyb6bhyrmyox6cxjztfka

Paralinguistics in speech and language—State-of-the-art and the challenge

Björn Schuller, Stefan Steidl, Anton Batliner, Felix Burkhardt, Laurence Devillers, Christian Müller, Shrikanth Narayanan
2013 Computer Speech and Language  
In addition, we present the new benchmark obtained by fusion of participants' predictions and conclude by discussing ten recent and emerging trends in the analysis of paralinguistics in speech and language  ...  This article aims to provide a broad overview of the constantly growing field by defining the field, introducing typical applications, presenting exemplary resources, and sharing a unified view of the  ...  This work was supported by a fellowship within the postdoc program of the German Academic Exchange Service (DAAD).  ... 
doi:10.1016/j.csl.2012.02.005 fatcat:2izbs3usxbgj5drbehlyknfciq

Acoustic and lexical representations for affect prediction in spontaneous conversations

Houwei Cao, Arman Savran, Ragini Verma, Ani Nenkova
2015 Computer Speech and Language  
For the analysis of acoustics, we zero in on the question of granularity. We confirm on our corpus that utterance-level features are more predictive than wordlevel features.  ...  We find that corpusdependent bag of words approach with mutual information between word and emotion dimensions is by far the best representation.  ...  For acoustic analysis, we use forced alignment between the audio and the manual transcripts to introduce a novel representation which proves to be highly advantageous for capturing affect-related cues  ... 
doi:10.1016/j.csl.2014.04.002 pmid:25382936 pmcid:PMC4219625 fatcat:ct6u5geofbeblhcoveu5al5nby

Analysis of acoustic and voice quality features for the classification of infant and mother vocalizations

Jialu Li, Mark Hasegawa-Johnson, Nancy L. McElwain
2021 Speech Communication  
Feature selection using Fisher scores and experiments of using weighted and unweighted samplers were also tested. Two datasets were evaluated: a benchmark dataset (CRIED) and our own corpus.  ...  We evaluate our classifiers on both benchmark dataset (the Cry Recognition In Early Development 3 J o u r n a l P r e -p r o o f Journal Pre-proof Analysis and classification of infant vocalizations Studies  ...  Data Benchmark data: CRIED database For benchmark evaluation, we tested all of our models on the CRIED database developed by Marschik et al. (2017) consisting of 5587 vocalizations of 20 infants (10  ... 
doi:10.1016/j.specom.2021.07.010 fatcat:w7g73pq6nbdqrezifc4hejbpqe

Communication, Language & Speech Deficits in Dementia (Research Data in Greek Population). [Abstract]

Dionysios Tafiadis
2017 Figshare  
2nd International Congress on Neurobiology, Psychopharmacology and Treatment Guidance. 24 – 27 of November 2011, Thessaloniki –Greece.  ...  Bridging art and science, her vision has culminated in a novel synthesis (The theoreti cal underpinnings of aff ecti ve temperaments: implicati ons for evoluti onary foundati ons of bipolarity and human  ...  Acknowledgements This study was conducted under the framework of DRUID European Integrated Project and was successfully completed with the close collaborati on of research teams from several European countries  ... 
doi:10.6084/m9.figshare.5263813.v1 fatcat:6eudgsjsqnbvtfvqnxq6tnj6c4

Monitoring Infant's Emotional Cry in Domestic Environments Using the Capsule Network Architecture

Mehmet Ali Tuğtekin Turan, Engin Erzin
2018 Interspeech 2018  
Active capsules at one level make predictions, via transformation matrices, for the parameters of higher-level capsules. When multiple predictions agree, a higher level capsule becomes active.  ...  We employed spectrogram representations from the short segments of an audio signal as an input of the CapsNet.  ...  In this context, INTERSPEECH 2018 ComParE challenge introduces a novel problem, which is to classify the three moodrelated infant vocalizations.  ... 
doi:10.21437/interspeech.2018-2187 dblp:conf/interspeech/TuranE18 fatcat:tr6kv56265bqvldk3h34prf3sm

Applying multiple classifiers and non-linear dynamics features for detecting sleepiness from speech

Jarek Krajewski, Sebastian Schnieder, David Sommer, Anton Batliner, Björn Schuller
2012 Neurocomputing  
Comparing different novel feature sets and classifiers for speech processing based fatigue detectionis is the primary aim of this study.  ...  Thus, we conducted a within-subject partial sleep deprivation design (20.00 -04.00 h, N = 77 participants) and recorded 372 speech samples of sustained vowel phonation.  ...  Thus, it seems likely that sleepiness detection could be improved by collecting similar-sized speech databases, containing speech samples from different types of speakers and speaking styles.  ... 
doi:10.1016/j.neucom.2011.12.021 fatcat:ze3qqjfbifdjldzxy4vlvccsou

Guest Editorial: Multimedia for Predictive Analytics

Sanjay Kumar Singh, Amit Kumar Singh, Basant Kumar, Subir Kumar Sarkar, Karm Veer Arya
2017 Multimedia tools and applications  
Finally, the editors are greateful to all Editorial Staff and publisher of the journal for their kind support for the processing of the publication of this special issue. Dr. Sanjay  ...  Acknowledgements First and foremost, the guest editors are heartily grateful to Prof.  ...  Singh and Srivastava introduce Deep learning for stock prediction and its performance is evaluated on Google stock price multimedia data (chart) from NASDAQ.  ... 
doi:10.1007/s11042-017-5107-x fatcat:mgp6pimnbzcypneluv43dujqcm

Ensemble of convolutional neural networks to improve animal audio classification

Loris Nanni, Yandre M. G. Costa, Rafael L. Aguiar, Rafael B. Mangolin, Sheryl Brahnam, Carlos N. Silla
2020 EURASIP Journal on Audio, Speech, and Music Processing  
Six different CNNs were tested, compared, and combined. Moreover, a further CNN, trained from scratch, was tested and combined with the fine-tuned CNNs.  ...  These features are evaluated, compared, and fused with the goal of producing better classification accuracy than other state-of-the-art approaches without ad hoc parameter optimization.  ...  of Higher Level Personnel (CAPES), and Araucária Foundation.  ... 
doi:10.1186/s13636-020-00175-3 fatcat:ftol6ozepbburcyi37dswpqodu

Multi-Modal Pain Intensity Assessment Based on Physiological Signals: A Deep Learning Perspective

Patrick Thiam, Heinke Hihn, Daniel A. Braun, Hans A. Kestler, Friedhelm Schwenker
2021 Frontiers in Physiology  
Traditional pain assessment approaches ranging from self-reporting methods, to observational scales, rely on the ability of an individual to accurately assess and successfully report observed or experienced  ...  traits such as in the case of professional athletes, who usually have a higher pain tolerance as regular individuals.  ...  ACKNOWLEDGMENTS We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Tesla K40 GPU used for this research.  ... 
doi:10.3389/fphys.2021.720464 pmid:34539444 pmcid:PMC8440852 fatcat:dymh6a2nlvedvbct6f72nozvsy

Advancing an Interdisciplinary Science of Conversation: Insights from a Large Multimodal Corpus of Human Speech [article]

Andrew Reece, Gus Cooney, Peter Bull, Christine Chung, Bryn Dawson, Casey Fitzpatrick, Tamara Glazer, Dean Knox, Alex Liebscher, Sebastian Marin
2022 arXiv   pre-print
We leverage the considerable scope of the corpus to (1) extend key findings from the literature, such as the cooperativeness of human turn-taking; (2) define novel algorithmic procedures for the segmentation  ...  In this report we advance an interdisciplinary science of conversation, with findings from a large, novel, multimodal corpus of 1,656 recorded conversations in spoken English.  ...  -Alexi Robichaux and Gabriella Kellerman in particular-for its sponsorship of this research and for BetterUp's willingness to share the data collected for research among the wider scientific community.  ... 
arXiv:2203.00674v1 fatcat:mezjuaeapnf4lkoyt4k6jkn4xu

Recognizing Continuous and Discontinuous Adverse Drug Reaction Mentions from Social Media Using LSTM-CRF

Buzhou Tang, Jianglu Hu, Xiaolong Wang, Qingcai Chen
2018 Wireless Communications and Mobile Computing  
ADR mentions from social media in medicine and investigate the effects of three factors on ADR mention recognition.  ...  To the best of our knowledge, this is the first time to investigate deep neural networks to mine continuous and discontinuous ADRs from social media.  ...  Acknowledgments This paper is supported in part by the following grants:  ... 
doi:10.1155/2018/2379208 fatcat:mt5z2l2xureozctqy3zwzsxq3i

Personalized Automatic Estimation of Self-reported Pain Intensity from Facial Expressions [article]

Daniel Lopez Martinez, Ognjen Rudovic, Rosalind Picard
2017 arXiv   pre-print
We show the benefits of the proposed personalized over traditional non-personalized approach on a benchmark dataset for pain analysis from face images.  ...  Personalization of the model is performed using a newly introduced facial expressiveness score, unique for each person.  ...  Acknowledgements The work of O. Rudovic is funded by European Union H2020, Marie Curie Action -Individual Fellowship no. 701236 (EngageMe).  ... 
arXiv:1706.07154v2 fatcat:6ullaz2drjacbktjv6wjte63ee

Personalized Automatic Estimation of Self-Reported Pain Intensity from Facial Expressions

Daniel Lopez Martinez, Ognjen Rudovic, Rosalind Picard
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We show the benefits of the proposed personalized over traditional non-personalized approach on a benchmark dataset for pain analysis from face images.  ...  Personalization of the model is performed using a newly introduced facial expressiveness score, unique for each person.  ...  Acknowledgements The work of O. Rudovic is funded by European Union H2020, Marie Curie Action -Individual Fellowship no. 701236 (EngageMe).  ... 
doi:10.1109/cvprw.2017.286 dblp:conf/cvpr/MartinezRP17 fatcat:jcqyhg5slvdtlns5iwwbph3hjy
« Previous Showing results 1 — 15 out of 2,727 results