Ira Gerson - Academia.edu (original) (raw)
Uploads
Papers by Ira Gerson
Text-to-speech conversion has traditionally been performed either by concatenating short samples ... more Text-to-speech conversion has traditionally been performed either by concatenating short samples of speech or by using rule-based systems to convert a phonetic representation of speech into an acoustic representation, which is then converted into speech. This paper describes a system that uses a time-delay neural network (TDNN) to perform this phonetic-to-acoustic mapping, with another neural network to control the timing of the generated speech. The neural network system requires less memory than a concatenation system, and performed well in tests comparing it to commercial systems using other technologies.
Dans un systeme de radiocommunications bidirectionnelles dans lequel des unites d'abonnes dis... more Dans un systeme de radiocommunications bidirectionnelles dans lequel des unites d'abonnes disposent de multiples fonctions provenant du logiciel s'executant dans un serveur, une interface utilisateur de l'unite d'abonne permet a l'utilisateur de l'unite d'abonne de changer l'etat de commande du logiciel serveur en fonction de differents types d'actionnements de l'interface utilisateur (fig. 3 numero 302). Selon un mode de realisation prefere, un, deux, ou plusieurs clics sur un commutateur d'entree a rappel, ainsi que d'appuyer, de maintenir et de relâcher (fig. 3 numero 310) le commutateur d'entree peut servir a selectionner ou deselectionner les differents services et applications fournies a l'unite d'abonne par le logiciel du serveur (fig. 3 numero 302).
Arxiv preprint cs/9811032, 1998
This paper describes the design of a neural network that performs the phonetic-to-acoustic mappin... more This paper describes the design of a neural network that performs the phonetic-to-acoustic mapping in a speech synthesis system. The use of a time-domain neural network architecture limits discontinuities that occur at phone boundaries. Recurrent data input also helps smooth the output ...
Electrical Engineering Handbook, 1999
Text-to-speech conversion has traditionally been performed either by concatenating short samples ... more Text-to-speech conversion has traditionally been performed either by concatenating short samples of speech or by using rule-based systems to convert a phonetic representation of speech into an acoustic representation, which is then converted into speech. This paper describes a system that uses a time-delay neural network (TDNN) to perform this phonetic-to-acoustic mapping, with another neural network to control the timing of the generated speech. The neural network system requires less memory than a concatenation system, and performed well in tests comparing it to commercial systems using other technologies.
Dans un systeme de radiocommunications bidirectionnelles dans lequel des unites d'abonnes dis... more Dans un systeme de radiocommunications bidirectionnelles dans lequel des unites d'abonnes disposent de multiples fonctions provenant du logiciel s'executant dans un serveur, une interface utilisateur de l'unite d'abonne permet a l'utilisateur de l'unite d'abonne de changer l'etat de commande du logiciel serveur en fonction de differents types d'actionnements de l'interface utilisateur (fig. 3 numero 302). Selon un mode de realisation prefere, un, deux, ou plusieurs clics sur un commutateur d'entree a rappel, ainsi que d'appuyer, de maintenir et de relâcher (fig. 3 numero 310) le commutateur d'entree peut servir a selectionner ou deselectionner les differents services et applications fournies a l'unite d'abonne par le logiciel du serveur (fig. 3 numero 302).
Arxiv preprint cs/9811032, 1998
This paper describes the design of a neural network that performs the phonetic-to-acoustic mappin... more This paper describes the design of a neural network that performs the phonetic-to-acoustic mapping in a speech synthesis system. The use of a time-domain neural network architecture limits discontinuities that occur at phone boundaries. Recurrent data input also helps smooth the output ...
Electrical Engineering Handbook, 1999