Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Diane Hirschfeld"'
Publikováno v:
INTERSPEECH
Autor:
Ivan Kraljevski, Diane Hirschfeld
Publikováno v:
INTERSPEECH
Autor:
Ivan Kraljevski, Diane Hirschfeld
Publikováno v:
INTERSPEECH
Publikováno v:
DSP for In-Vehicle and Mobile Systems ISBN: 0387229787
The article deals with a novel speech recognizer technology which has the potential to overcome some problems of in-car speech control. The verbKEY recognizer bases on the Associative-Dynamic (ASD) algorithm which differs from established techniques
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bcd79a213435d88a4646e0d65280c6bf
https://doi.org/10.1007/0-387-22979-5_12
https://doi.org/10.1007/0-387-22979-5_12
Publikováno v:
8th European Conference on Speech Communication and Technology (Eurospeech 2003).
Autor:
Diane Hirschfeld
Publikováno v:
6th International Conference on Spoken Language Processing (ICSLP 2000).
Autor:
Diane Hirschfeld, Matthias Wolff
Publikováno v:
6th International Conference on Spoken Language Processing (ICSLP 2000).
Publikováno v:
5th International Conference on Spoken Language Processing (ICSLP 1998).
Autor:
Heinz Dieter Maas, Diane Hirschfeld
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783540617082
KI
KI
The quality-improvement of a speech synthesis system is tightly linked with the generation of natural sounding prosody. Reliable accentuation and structuring of the text based on syntactic knowledge are prerequisites for this goal. After the implemen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::77b53f9c78b6ab90eeea6c205d5d91f7
https://doi.org/10.1007/3-540-61708-6_52
https://doi.org/10.1007/3-540-61708-6_52
Autor:
Diane Hirschfeld
Publikováno v:
The Journal of the Acoustical Society of America. 105:1030-1030
In database preparation for concatenative speech synthesis, the alignment of canonical and pronunciation form phone sequences plays a key role for further processing. Syllabification and word boundary detection are based on canonical transcriptions,