2013
DOI: 10.1109/tce.2013.6626261
|View full text |Cite
|
Sign up to set email alerts
|

Audio-based age and gender identification to enhance the recommendation of TV content

Abstract: Recommending TV content to groups of viewers is best carried out when relevant information such as the demographics of the group is available. However, it can be difficult and time consuming to extract information for every user in the group. This paper shows how an audio analysis of the age and gender of a group of users watching the TV can be used for recommending a sequence of N short TV content items for the group. First, a state of the art audio-based classifier determines the age and gender of each user … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
7
0
3

Year Published

2014
2014
2021
2021

Publication Types

Select...
4
4

Relationship

2
6

Authors

Journals

citations
Cited by 17 publications
(10 citation statements)
references
References 17 publications
0
7
0
3
Order By: Relevance
“…There have been several works that have utilized textindependent attributes from speech to recommend items. In [16] the authors used age-and-gender profiles extracted from the speech of home users to recommend TV advertisements to them. In another study, emotions were extracted from speech and used in mood profiles to propose initial recommendations [17].…”
Section: Using Closed-set Speaker Identification Scorementioning
confidence: 99%
“…There have been several works that have utilized textindependent attributes from speech to recommend items. In [16] the authors used age-and-gender profiles extracted from the speech of home users to recommend TV advertisements to them. In another study, emotions were extracted from speech and used in mood profiles to propose initial recommendations [17].…”
Section: Using Closed-set Speaker Identification Scorementioning
confidence: 99%
“…Current gender recognition techniques in literature have been applied to various types of data including those that are image-based [2][3][4] , audio-based [1,5,6] or gait-based [7][8][9][10][11] to name a few. Wu et al [12] categorize approaches into appearancebased approaches which include static-body, dynamic-body and apparel features in contrast to non-appearance based approaches which include data types such as speech, iris, voice and fingerprints.…”
Section: Data Capturementioning
confidence: 99%
“…Much effort has been devoted to automatically determining demographic properties such as gender, age, and ethnicity. A system that accurately distinguishes between genders is also useful for demographic studies [1] . This has prompted interest in the computer vision community to pursue an explanation or representation of the way the human brain and visual system perceives and interprets another being as male or female by means of an automated system.…”
Section: Introductionmentioning
confidence: 99%
“…Veritabanındaki yaş gruplarının belirlenmesinde benzer çalışmalarda [5] kullanılan yaş aralıkları temel alınmıştır. Buna göre çocuk sınıfı için 0-15 yaş aralıgı, genç sınıfı için 15-30 yaş aralıgı, orta yaş için 30-50 yaş aralıgı ve yaşlı sınıfı için ise 50 yaş üstü kullanılmıştır.…”
Section: A Veritabanının Oluşturulmasıunclassified