16,341 Hits in 6.1 sec

Multiple topic identification in human/human conversations

X. Bost, G. Senay, M. El-Bèze, R. De Mori
2015 Computer Speech and Language  
Furthermore, in certain conversations theme mentions are localized in specific conversation segments while in other conversations mentions cannot be localized.  ...  Due to the unpredictable type of theme mentions, it is appropriate to consider methods for theme hypothesization based on global as well as local feature extraction.  ...  of one of the above mentioned 8 theme labels obtained with Gaussian and svm classifiers using different types of features including lda hidden topic features computed in a single hidden space. 6.3.  ... 
doi:10.1016/j.csl.2015.03.006 fatcat:45ygeetrbbf45gokus23ry7sxu

A Survey of Speaker Recognition: Fundamental Theories, Recognition Methods and Opportunities

Muhammad Mohsin Kabir, M. F. Mridha, Jungpil Shin, Israt Jahan, Abu Quwsar Ohi
2021 IEEE Access  
Further, the performance of current speaker recognition systems are investigated in this survey with the limitations and possible ways of improvement.  ...  Specifically, this literature survey gives a concise introduction to ASR and provides an overview of the general architectures dealing with speaker recognition technologies, and upholds the past, present  ...  , original disappeared features and heterogeneous feature types. [22] 2011 Overview on text-independent, closed-set, speaker identification in the modelling and classification paradigms with key extracted  ... 
doi:10.1109/access.2021.3084299 fatcat:6eavwhxg6jfwngu7bnwzjc4w3q

Detecting and tracking ongoing topics in psychotherapeutic conversations

Ilyas Chaoua, Diego Reforgiato Recupero, Sergio Consoli, Aki Härmä, Rim Helaoui
2018 International Joint Conference on Artificial Intelligence  
Topics detection helps in summarizing the semantic themes used during the therapeutic conversations, and in predicting a specific topic for each talk-turn.  ...  We present an alternative way to look at face-to-face conversations in conjunction with a new approach that combines topic modeling and transitions matrices to elicit valuable knowledge.  ...  PLDA is often very useful for applications with a human in the loop, since induced classes correspond well with human categorization, as represented by the provided label space.  ... 
dblp:conf/ijcai/ChaouaRCHH18 fatcat:olxbov3ujvcotbrr4guvb5ryam

The Agent of Truth: Reflections on Robert Sokolowski's Phenomenology of the Human Person

Molly Brigid Flynn
2012 New Yearbook for Phenomenology and Phenomenological Philosophy  
A related theme that interests me is Sokolowski's identification of philosophy with a reflection on the "conversation of mankind."  ...  Like philosophy in the human conversation, persons are neither submerged in nor detached from the world known to them and expressed in their predications.  ... 
doi:10.1558/nyppp.v10i1.319 fatcat:izgbh3oqafailjqwxg5cz7jemy

Ecological discourse analysis: theory and practice – a summary of New developments of ecological discourse analysis

Ming Cheng
2022 Journal of World Languages  
Consequently, it constructs the theoretical systems of ecological discourse analysis from the perspective of ecolinguistics: the transitivity system, mood system, appraisal system, Theme system, cohesion  ...  This book presents readers with a comprehensive and applicable analytical framework for ecological discourse analysis, that is, "ecological grammar".  ...  Multiple Theme consists of three kinds of combinations of Themes: the first is two kinds: life and lifeless; the former specifies the human and non-human types in terms of the species category, and the  ... 
doi:10.1515/jwl-2021-0030 fatcat:a2coimmv3bgy5bmtyh3c3wvqlm

Fifty years of progress in speech and speaker recognition

Sadaoki Furui
2004 Journal of the Acoustical Society of America  
Research in automatic speech and speaker recognition has now spanned five decades.  ...  A much greater understanding of the human speech process is required before automatic speech and speaker recognition systems can approach human performance.  ...  The program was focusing on natural, unconstrained human-human speech from broadcasts and foreign conversational speech in multiple languages.  ... 
doi:10.1121/1.4784967 fatcat:6rz6ndilzfcbfnxrssc3sgfn2u

Speech Recognition by Machine, A Review [article]

M. A. Anusuya, S. K. Katti
2010 arXiv   pre-print
of Speech Recognition system requires careful attentions to the following issues: Definition of various types of speech classes, speech representation, feature extraction techniques, speech classifiers  ...  This paper presents a brief survey on Automatic Speech Recognition and discusses the major themes and advances made in the past 60 years of research, so as to provide a technological perspective and an  ...  The program was focusing on natural, unconstrained human speech from broadcasts and foreign conversational speech in multiple languages.  ... 
arXiv:1001.2267v1 fatcat:yvcif2cb2jgkbjcqreid7cxanu

Spectral Subband Centroids for Robust Speaker Identification Using Marginalization-based Missing Feature Theory

Aaron Nicolson, Signal Processing Laboratory,Griffith University, Brisbane, Australia, Jack Hanson, James Lyons, Kuldip Paliwal
2018 International Journal of Signal Processing Systems  
Our results show that SSCs as features produce a more robust marginalization-based MFT, diagonal-covariance GMM-based, Automatic Speaker Identification (ASI) system than LSSEs as features, for at all tested  ...  These features are highly correlated, thus suboptimal for classification with diagonal-covariance Gaussian Mixture Models (GMMs), a common classifier in marginalization-based MFT.  ...  INTRODUCTION The aim of an Automatic Speaker Identification (ASI) system is to determine a person's identity from a database of known speakers, given a recording of their speech.  ... 
doi:10.18178/ijsps.6.1.12-16 fatcat:u4qwyohukjdodovpmbbw4imfm4

Introduction to Voice Presentation Attack Detection and Recent Advances [article]

Md Sahidullah, Hector Delgado, Massimiliano Todisco, Tomi Kinnunen, Nicholas Evans, Junichi Yamagishi, Kong-Aik Lee
2019 arXiv   pre-print
This chapter summarises the progress, with a focus on studies completed in the last three years.  ...  Over the past few years significant progress has been made in the field of presentation attack detection (PAD) for automatic speaker recognition (ASV).  ...  human speakers [62, 63] .  ... 
arXiv:1901.01085v1 fatcat:4dxlmlyflzgnjc7jic2fwm3s6e

50 Years of Progress in Speech and Speaker Recognition Research

Sadaoki Furui
1970 ECTI Transactions on Computer and Information Technology  
Research in automatic speech and speaker recognition has now spanned five decades.  ...  A much greater understanding of the human speech process is required before automatic speech and speaker recognition systems can approach human performance.  ...  An utterance was characterized as a sequence of transitions through a 5-state HMM in the acoustic feature space.  ... 
doi:10.37936/ecti-cit.200512.51834 fatcat:kac4i7titbagzfnqafkws56o6q

Exploring Users' Mental Models for Anthropomorphized Voice Assistants through Psychological Approaches

Dasom Park, Kiechan Namkung
2021 Applied Sciences  
The first structure is of users who feel human-like empathy and warmth in the use of VA. Meanwhile, the second structure is of users who seek help with problem-solving.  ...  Using two types of psychological approaches that were not applied in previous studies, this research analyzed users' mental models.  ...  "I wanted to express a speaker in an intangible space. Human life is finite, but speakers are infinite, so it seems that it will continue to develop in the future."  ... 
doi:10.3390/app112311147 fatcat:w7ryui7ybva35cmbl2tj5qzzsa

Microvariation, variation, and the features of universal grammar

Mark Hale, Madelyn Kissock, Charles Reiss
2007 Lingua  
from phonological computation by the fact that it incorporates some type of conversion process-it changes one type of representation (featural, for example) into another type of representation (gestural  ...  We assume that these two transducers are innate and invariant-they are identical in all humans (barring some specific neurological impairment) and do not change over time or experience (i.e., they do not  ...  Acknowledgements The authors would like to thank the audiences of the 6e Journées Internationales du Réseau Français de Phonologie (June 2004) and the 25th GLOW Colloquium in Amsterdam (May 2002) as well  ... 
doi:10.1016/j.lingua.2006.03.009 fatcat:aczwhzthtbfbdhdoibdq3ydfpa

Search for Hidden Knowledge in Collective Intelligence dealing Indeterminacy Ontology of Folksonomy with Linguistic Pragmatics and Quantum Logic [article]

Massimiliano Dal Mas
2011 arXiv   pre-print
Vector space retrieval has been proven efficiency when there isn't a data behavioural because it bears ranking algorithms involving a small number of types of elements and few operations.  ...  This work aims to explore ways to make explicit and available the tacit knowledge hidden in the collective intelligence of a collaborative environment within organizations.  ...  The type of exclusion which arises from incompatible frameworks is easily confused with, in fact it is quite different from the sort of exclusion which arises all the time.  ... 
arXiv:1105.4868v1 fatcat:dqhtzctt6fajflg4dr5z7qcauu

Automatic nonverbal analysis of social interaction in small groups: A review

Daniel Gatica-Perez
2009 Image and Vision Computing  
Small group conversations are a specific case on which much of this work has been conducted.  ...  management, internal states, personality traits, and social relationships in small group conversations, along with pointers to the relevant literature in social science.  ...  with Distant Access (AMIDA), and the US research program on Video Analysis and Content Extraction (VACE).  ... 
doi:10.1016/j.imavis.2009.01.004 fatcat:melyg25zhvcvbj2mthf5wmqcgq

A Survey of Available Corpora for Building Data-Driven Dialogue Systems [article]

Iulian Vlad Serban, Ryan Lowe, Peter Henderson, Laurent Charlin, Joelle Pineau
2017 arXiv   pre-print
During the past decade, several areas of speech and language understanding have witnessed substantial breakthroughs from the use of data-driven models.  ...  In the area of dialogue systems, the trend is less obvious, and most practical systems are still built through significant engineering and expert knowledge.  ...  Early versions of the manuscript benefited greatly from the proofreading of Melanie Lyman-Abramovitch, and later versions were extensively revised by Genevieve Fried and Nicolas Angelard-Gontier.  ... 
arXiv:1512.05742v3 fatcat:lh34cnbvefcfxp2qwxfyiuuwhm
« Previous Showing results 1 — 15 out of 16,341 results