4   Artículos

 
en línea
Hyeon-Kyu Noh and Hong-June Park    
A convolutional neural network (CNN) transducer decoder was proposed to reduce the decoding time of an end-to-end automatic speech recognition (ASR) system while maintaining accuracy. The CNN of 177 k parameters and a kernel size of 6 generates the proba... ver más
Revista: Applied Sciences    Formato: Electrónico

 
en línea
Kadria Ezzine, Joseph Di Martino and Mondher Frikha    
We present an any-to-one voice conversion (VC) system, using an autoregressive model and LPCNet vocoder, aimed at enhancing the converted speech in terms of naturalness, intelligibility, and speaker similarity. As the name implies, non-parallel any-to-on... ver más
Revista: Applied Sciences    Formato: Electrónico

« Anterior     Página: 1 de 1     Siguiente »