Audiovisual speaker localization in medium smart meeting room

Ronzhin, Andrey; Budkov, Victor

doi:10.1109/icics.2011.6173618

Cited by 9 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Предложенный метод распознавания лиц основан на применении модифицированных методов LBP [33] и PCA [31] и успешно был апробирован в системе автоматической регистрации участников мероприятия в интеллектуальном зале [34,35]. Многоэтапная процедура мониторинга зон зала позволяет найти присутствующих в нем участников и записать аудиовизуальные данные, необходимые для проведения идентификации личности присутствующих.…”

Section: рис 3 каталог типовых нелинейных характеристикunclassified

The Concept of Building Intelligent Systems Management for Protected Objects Decentralized Energy

Чубраева¹,

Ронжин²,

Шишлаков³

et al. 2014

SPIIRAS Proc.

View full text Add to dashboard Cite

Ф. Концепция построения интеллектуальных защищенных систем управления для объектов децентрализованной энергетики. Аннотация. Рассматриваются вопросы повышения энергоэффективности электроэнергетических комплексов децентрализованной энергетики со сверхпроводниковым оборудованием за счет использования интеллектуальной защищенной диалоговой системы автоматического управления, выполняющей адаптацию комплекса к режимам работы, а также внешним возмущающим воздействиям и проводящей биометрический контроль доступа операторов. Ключевые слова: сверхпроводниковое оборудование, электроэнергетический комплекс, диалоговая защищенная система, биометрическая идентификация личности, распознавание лиц, обобщенный метод Галеркина, интеллектуальное управление.Chubraeva L.I., Ronzhin An.L., Shyshlakov A.V., Ronzhin Al.L., Shyshlakov V.F. The concept of development of intelligent protected control systems for objects of decentralized energetics. Abstract. The issues of energy efficiency of decentralized power complexes with superconducting equipment through the use of intelligent protected dialogue system for automatic control, which performs the adaptation to the complex modes of operation, external perturbations and conducting biometric access control of operators, are considered.

show abstract

Section: рис 3 каталог типовых нелинейных характеристикunclassified

The Concept of Building Intelligent Systems Management for Protected Objects Decentralized Energy

Чубраева¹,

Ронжин²,

Шишлаков³

et al. 2014

SPIIRAS Proc.

View full text Add to dashboard Cite

show abstract

“…Events and behaviours can be modelled in the context of related visual recognized objects. Previous works [1][2] [3] are still unable to visually localize speaker of the meeting rooms and need the help of audio features to identify the speaker. Other researchers [4][5] [6] explained smart meeting rooms modelling but did not focused on visual events and behaviours which are important features of smart room systems.…”

Section: Introductionmentioning

confidence: 99%

“…This paper aims to focus on visual events or behaviours in the smart meeting room systems including visual localization of the speaker. Research done by [1] uses predefined chair and speaker position. However, in the real situation without predefined scenarios, problems still occur in correctness of object identification due to various object position and illumination [7].…”

Section: Introductionmentioning

confidence: 99%

Object Localization and Activities Identification Using Attribute Details in SMART Meeting Rooms

Andriana¹,

Prihatmanto²,

Hidayat³

et al. 2018

Computer Science &Amp; Information Technology

View full text Add to dashboard Cite

This paper is concerned with the development of interactive systems for smart meeting rooms. Automated recognition of video events is an important research area. We present an LTL (Linear Temporal Logic) model of basic objects and activities recognition in smart meeting rooms using object attribute details. There are still problems of misrecognizing objects in existing visual recognition methods because lack of enough feature attributive information details. This paper investigates morphological approach to increase recognition accuracy using variability in a limited area of moving object using object attribute details. The proposed methods are also compared to popular and recent methods of visual object and event recognition.

show abstract

“…In that sense, this area of machine hearing considers the use of spatial audio recordings, along with systems inspired by human hearing, to enhance the detection and localization of sounds. Several applications relate to machine hearing, such as intelligent meeting rooms [2], helping deaf people to know the sounds of their environment [3], [4], and acoustic monitoring of urban environments or wildlife [5], [6].…”

mentioning

confidence: 99%

Sound Events Localization and Detection Using Bio-inspired Gammatone Filters and Temporal Convolutional Neural Networks

Rosero¹,

Grijalva²,

Masiero³

2022

Preprint

View full text Add to dashboard Cite

<p>This manuscript addresses the problem of detecting, classifying, and localizing sound sources in an acoustic scene of spatial audio. We propose using bio-inspired Gammatone auditory filters for the acoustic feature extraction stage and a novel deep learning architecture encompassing convolutional, recurrent, and temporal convolutional blocks. Our system exceeded the state-of-the-art metrics on four spatial audio datasets with different levels of acoustical complexity and up to three sound sources overlapping in time. Furthermore, we also performed a comparative analysis of the gap between machine and human hearing, evidencing that our results have already exceeded the human performance in non-reverberant scenarios. </p>

show abstract

Audiovisual speaker localization in medium smart meeting room

Cited by 9 publications

References 12 publications

The Concept of Building Intelligent Systems Management for Protected Objects Decentralized Energy

The Concept of Building Intelligent Systems Management for Protected Objects Decentralized Energy

Object Localization and Activities Identification Using Attribute Details in SMART Meeting Rooms

Sound Events Localization and Detection Using Bio-inspired Gammatone Filters and Temporal Convolutional Neural Networks

Contact Info

Product

Resources

About