2013
DOI: 10.1016/j.csl.2012.02.005
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: Paralinguistic analysis is increasingly turning into a mainstream topic in speech and language processing. 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 chain of processing. It then presents the first broader Paralinguistic Challenge organised at INTERSPEECH 2010 by the authors including a historical overview of the Challenge tasks of recognising age, gender… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
153
0
6

Year Published

2013
2013
2017
2017

Publication Types

Select...
6
2
1

Relationship

2
7

Authors

Journals

citations
Cited by 244 publications
(159 citation statements)
references
References 156 publications
0
153
0
6
Order By: Relevance
“…Many previous studies focused on the correlations of formal, measurable features and the underlying communicative or linguistic phenomena such as speech acts [15], topic structure [16,21] and some paralinguistically relevant properties like age, gender and expressed emotions of the speakers [17]. Beyond the theoretical questions, the main practical challenge of these studies is how we can make the content -which is readily accessible for humans -machine-readable (detectable or predictable) based on physically measurable acoustic parameters.…”
Section: Introductionmentioning
confidence: 99%
“…Many previous studies focused on the correlations of formal, measurable features and the underlying communicative or linguistic phenomena such as speech acts [15], topic structure [16,21] and some paralinguistically relevant properties like age, gender and expressed emotions of the speakers [17]. Beyond the theoretical questions, the main practical challenge of these studies is how we can make the content -which is readily accessible for humans -machine-readable (detectable or predictable) based on physically measurable acoustic parameters.…”
Section: Introductionmentioning
confidence: 99%
“…Ancak ergenlik öncesinde çocuk seslerinden cinsiyet ayrımı yapılamadığı için çocuk sesleri genellikle tek sınıfta değerlendirilir. Günümüzde sesten yaş ve cinsiyet sınıflandırma konusunda genellikle üç kategori kullanılmaktadır [1]. Bunlardan cinsiyet kategorisinde konuşmacılar çocuk, erkek ve bayan olmak üzere üç gruba; yaş kategorisinde ise çocuk, genç, yetişkin ve yaşlı olarak dört gruba ayrılmaktadır.…”
Section: Gi̇ri̇ş (Introduction)unclassified
“…It is another central paralinguistic problem with other applications ranging from ASR systems and call centers to intelligent user interfaces [28]. Work on noise robustness in speech emotion recognition has also been started [27,32], but to our knowledge, signal denoising has not been explicitly studied for this purpose.…”
Section: Introductionmentioning
confidence: 99%
“…Of these, intelligibility, whose improvement is the more di cult problem [16], is potentially relevant for ASR. Computational paralinguistic analysis of speech, whose general aim is to uncover various external attributes of speech not related to its linguistic message (the concern of ASR), has emerged as an active field of research within the past decade [28]. Two of its most central topics are speaker recognition (identification and verification) and, more recently, automatic recognition of emotion in speech.…”
Section: Introductionmentioning
confidence: 99%