Encontrados 10 documentos, a visualizar página 1 de 1
Spectral multi-normalisation for robust speech recognition
Lima, C. S.; Almeida, Luís B.; Tavares, Adriano; Silva, Carlos A.This paper presents an improved version of a spectral normalisation based method for extraction of speech robust features in additive noise. The baseline normalisation method was developed by taking into consideration that, while the speech regions with less energy need more robustness, since in these regions the noise is more dominant, the “peaked” spectral regions which are the most reliable due to the higher...
Continuous environmental adaptation of a speech recognizer in telephone line co...
Lima, C. S.; Almeida, Luís B.; Monteiro, João L.This paper presents a maximum likelihood (ML) approach, relative to the background model estimation, in noisy acoustic non-stationary environments. The external noise source is characterised by a time constant convolutional and a time varying additive components, which is consistent with the telephone channel. The HMM composition technique, provides a mechanism for integrating parametric models of acoustic back...
Improving the role of unvoiced speech segments by spectral normalisation in rob...
Lima, C. S.; Almeida, Luís B.; Monteiro, João L.This paper presents a spectral normalisation based method for extraction of speech robust features in additive noise. The method has two main goals: 1) The “peaked” spectral zones, where the most speech energy is concentrated must be preserved (from clean to noisy speech features) as much as possible by the feature extraction process. Usually, these spectral regions are the most reliable due to the higher spee...
A robust feature extraction for automatic speech recognition in noisy environments
Lima, C. S.; Almeida, Luís B.; Monteiro, João L.This paper presents a method for extraction of speech robust features when the external noise is additive and has white noise characteristics. The process consists of a short time power normalisation which goal is to preserve as much as possible, the speech features against noise. The proposed normalisation will be optimal if the corrupted process has, as the noise process white noise characteristics. With opti...
Robótica'2001 - Festival Nacional de Robótica
Almeida, Luís B.; Azevedo, José; Cardeira, Carlos; Fonseca, Pedro; Lima, Pedro; Ribeiro, António Fernando; Santos, V.O ROBÓTICA’2001 – Festival Nacional de Robótica visa promover desenvolvimentos técnicos e científicos na área da Robótica Móvel e áreas afins (electrónica, mecânica, programação, visão por computador, inteligência artificial, navegação, controlo, etc) através de um problema motivador, a ser resolvido por diferentes grupos de investigadores e estudantes. Procura-se ainda difundir a Ciência e a Tecnologia junto d...
Mobile robot competitions : fostering advances in research, development and edu...
Almeida, Luís B.; Azevedo, José; Cardeira, Carlos; Costa, Paulo; Fonseca, Pedro; Lima, Pedro; Ribeiro, António Fernando; Santos, V.Mobile robot competitions are events well suited to experimentation, research and development in many areas concerned with science and technology, ranging from material science to artificial intelligence. Aware of this fact, and for several years now, some Portuguese Universities have been involving some of their Engineering and Computer Science students in such contests, namely those of international level. Th...
Adaptive technique for ATM call admission and routing control using traffic pre...
Neves, Joaquim E.; Leitão, Mário J.; Almeida, Luís B.This paper discusses a technique for call admission and routing control, based on a global quality function, which is dependent on the allocated bandwidth, the free network capacity and the call rejection rate, and incorporates quality of service functions, predicted by neural networks. The superior capability of this technique to support admission and routing decisions, according to the characteristics of the ...
Neural networks in B-ISDN flow control : ATM traffic prediction or network mode...
Neves, Joaquim E.; Leitão, Mário J.; Almeida, Luís B.The authors discuss a technique that offers the combination of shared bandwidth and rejection rate parameters, together with the quality of service predicted by neural networks in a novel strategy for connection admission control and call routing.
B-ISDN connection admission control and routing strategy with traffic predictio...
Neves, Joaquim E.; Almeida, Luís B.; Leitão, Mário J.The resource allocation in the Broadband Integrated Services Digital Network (B-ISDN) can be based in an overall network performance function described in this paper and named quality of operation. The quality of operation function is determined itself by bandwidth and quality of service functions. The traffic patterns of the quality of service for each call are predicted by neural networks. The applicability...
ATM call control by neural networks
Neves, Joaquim E.; Almeida, Luís B.; Leitão, Mário J.The resource allocation in the Broadband Integrated Services Digital Network (B-ISDN) must guarantee the quality of service negotiated with new and existing calls, taking into account the Asynchronous Transfer Mode (ATM) statistical characteristics. A quality of operation function, characterizing the overall network performance, is proposed, and based on this function, it is introduced a new strategy for the ad...
| Financiadores do RCAAP | |||||||
|
|
|
|
|
|
||