Speaker Recognition Using Dynamic Features and The Null Space Combination of Classifiers in The Sub-band Domain
This paper investigates the inclusion of dynamic features in the input vectors used by the multiple classification scheme which employ the null space to co...
- Eduardo Esteves Vale
- Abraham Alcaim
- Rosângela Coelho
- Delta features
- delta-delta features
- multiple subband-classifiers
- speaker recognition
SBrT 2010
Lossless Multi-Grid Chain Code with Optimized Cell Usage for Contour Description of Visual Objects
In the context of object-based image compression, shape encoders that describe the contour of the objects, called chain codes, tend to be more efficient th...
- Fabiana O. P. Fernandes
- Willian G. de Almeida
- Flávia M. Freitas
- Abraham Alcaim
- shape encoding
- object-based image compression
- MPEG-4
- chain code
- grid cell
SBrT 2010
Segregação de Voz Usando Mascaramento INM sobre o Banco de Filtros Gammatone
This paper presents an innovative approach that employs an ideal neighbourhood mask (INM) that has the ability to efficiently use Local Binary Pattern (LBP...
- Christian Arcos Gordillo
- Marley Vellasco
- Abraham Alcaim
- Enhancement
- mask
- Neighborhood
- TimeFrequency
- noise.
SBrT 2018
Comparação dos Atributos MFCC, SSCH e PNCC para Reconhecimento Robusto de Voz Contínua
Este artigo compara o desempenho do reconhecimento de voz contínua – corrompida por ruído aditivo – utilizando três tipos de atributos: MFCC, SSCH e PNCC. ...
- Jan Krueger Siqueira
- Abraham Alcaim
- Reconhecimento Robusto de Voz Contínua
- ruído
- MFCC
- SSCH
- PNCC
- HTK
- TIMIT
- NOISEX-92.
SBrT 2011
Reconhecimento de Voz Contínua com Atributos PNCC e Métodos de Robustez WD e MAP
The degradation of the speech signal due to adverse conditions generates low accuracy rates in speech recognition systems. The authors propose mixing two m...
- Christian Dayan Arcos
- Marco Antonio Grivet
- Abraham Alcaim
- Signal
- degradation
- enhancement
- compensation
- attributes
SBrT 2013