Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 9 de 9
Filtrar
Más filtros











Base de datos
Intervalo de año de publicación
1.
J Healthc Eng ; 2022: 6005446, 2022.
Artículo en Inglés | MEDLINE | ID: mdl-35388315

RESUMEN

Human-computer interaction (HCI) has seen a paradigm shift from textual or display-based control toward more intuitive control modalities such as voice, gesture, and mimicry. Particularly, speech has a great deal of information, conveying information about the speaker's inner condition and his/her aim and desire. While word analysis enables the speaker's request to be understood, other speech features disclose the speaker's mood, purpose, and motive. As a result, emotion recognition from speech has become critical in current human-computer interaction systems. Moreover, the findings of the several professions involved in emotion recognition are difficult to combine. Many sound analysis methods have been developed in the past. However, it was not possible to provide an emotional analysis of people in a live speech. Today, the development of artificial intelligence and the high performance of deep learning methods bring studies on live data to the fore. This study aims to detect emotions in the human voice using artificial intelligence methods. One of the most important requirements of artificial intelligence works is data. The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) open-source dataset was used in the study. The RAVDESS dataset contains more than 2000 data recorded as speeches and songs by 24 actors. Data were collected for eight different moods from the actors. It was aimed at detecting eight different emotion classes, including neutral, calm, happy, sad, angry, fearful, disgusted, and surprised moods. The multilayer perceptron (MLP) classifier, a widely used supervised learning algorithm, was preferred for classification. The proposed model's performance was compared with that of similar studies, and the results were evaluated. An overall accuracy of 81% was obtained for classifying eight different emotions by using the proposed model on the RAVDESS dataset.


Asunto(s)
Inteligencia Artificial , Habla , Computadores , Emociones , Femenino , Humanos , Masculino , Redes Neurales de la Computación
2.
Acta Crystallogr Sect E Struct Rep Online ; 67(Pt 9): o2224, 2011 Sep 01.
Artículo en Inglés | MEDLINE | ID: mdl-22065130

RESUMEN

In the title compound, C(12)H(11)Br(2)NO(2)S, the dihedral angle between the two rings is 78.79 (12)°. The crystal packing features C-H⋯π inter-actions.

3.
Acta Crystallogr Sect E Struct Rep Online ; 67(Pt 5): o1240-1, 2011 May 01.
Artículo en Inglés | MEDLINE | ID: mdl-21754534

RESUMEN

In the title compound, C(23)H(19)NO(4)S(2), the indole ring system makes dihedral angles of 89.6 (1) and 84.5 (8)° with the phenyl-sulfonyl and phenyl-sulfanyl rings, respectively. In the crystal, the mol-ecules are linked into C(10) chains running along the c axis by an inter-molecular C-H⋯O hydrogen bond. In addition, the crystal packing is stabilized by C-H⋯π inter-actions.

4.
Acta Crystallogr Sect E Struct Rep Online ; 65(Pt 3): o483, 2009 Feb 06.
Artículo en Inglés | MEDLINE | ID: mdl-21582152

RESUMEN

In the mol-ecule of the title compound, C(17)H(17)NO(5)S, the two aromatic rings are oriented at an angle of 30.13 (10)°. The ethyl acetate group assumes an extended conformation. Mol-ecules are linked into C(7) chains running along the a axis by inter-molecular C-H⋯O hydrogen bonds, and the chains are crosslinked via C-H⋯π inter-actions, with the sulfonyl-bound phenyl ring acting as an acceptor.

5.
Acta Crystallogr Sect E Struct Rep Online ; 65(Pt 3): o530, 2009 Feb 18.
Artículo en Inglés | MEDLINE | ID: mdl-21582191

RESUMEN

In the title compound, C(17)H(17)NO(5)S, the N atom is sp(3)-hybridized and the S atom has a distorted tetra-hedral configuration. The dihedral angle between the two aromatic rings is 30.0 (1)°, and that between the ethyl acetate group and the formyl-phenyl ring is 77.4 (1)°. The mol-ecules are linked into chains along [100] by C-H⋯O hydrogen bonds and the chains are linked via C-H⋯π inter-actions.

6.
Acta Crystallogr Sect E Struct Rep Online ; 65(Pt 3): o531, 2009 Feb 18.
Artículo en Inglés | MEDLINE | ID: mdl-21582192

RESUMEN

In the title compound, C(14)H(13)NO(4)S, the mean planes of the pyrrole and phenyl rings form a dihedral angle of 88.7 (1)°. The aldehyde groups are slightly twisted from the pyrrole plane. In the crystal structure, mol-ecules are linked into a three-dimensional framework by C-H⋯O hydrogen bonds.

7.
Acta Crystallogr Sect E Struct Rep Online ; 65(Pt 10): o2455, 2009 Sep 12.
Artículo en Inglés | MEDLINE | ID: mdl-21577910

RESUMEN

In the title compound, C(18)H(20)O(8)S(2), the dihedral angle between the two thio-phene rings is 2.33 (7)°. The methyl C atoms of the ester groups are disordered over two positions; the site-occupancy factors of the terminal methyl C atoms are 0.632 (18):0.368 (18) and 0.623 (17):0.377 (17). The mol-ecular structure is stabilized by weak intra-molecular C-H⋯O inter-actions and the crystal structure is stabilized through weak inter-molecular C-H⋯O inter-actions.

8.
Acta Crystallogr Sect E Struct Rep Online ; 65(Pt 11): o2790, 2009 Oct 17.
Artículo en Inglés | MEDLINE | ID: mdl-21578382

RESUMEN

In the title compound, C(30)H(32)O(8)S(2), the dihedral angle between the two benzene rings is 18.8 (1)°. The mol-ecular structure is stabilized by weak intra-molecular C-H⋯O hydrogen bonds. In the crystal structure, the mol-ecules are linked via weak inter-molecular C-H⋯O hydrogen bonds and π-π inter-actions between two benzene rings [centroid-centroid distance = 3.672 (1) Å].

SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA