Sciweavers

36 search results - page 2 / 8
» Conventional Signalling Acts and Conversation
Sort
View
ICMCS
2005
IEEE
124views Multimedia» more  ICMCS 2005»
13 years 11 months ago
Efficient conversion method between subband domain representations
This paper presents an efficient method for the conversion between subband domain representations of different filter banks. It advantageously replaces the conventional cascade of...
Abdellatif Benjelloun Touimi, Adil Mouhssine
ICASSP
2011
IEEE
12 years 9 months ago
A multi-stream ASR framework for BLSTM modeling of conversational speech
We propose a novel multi-stream framework for continuous conversational speech recognition which employs bidirectional Long Short-Term Memory (BLSTM) networks for phoneme predicti...
Martin Wöllmer, Florian Eyben, Björn Sch...
ICASSP
2008
IEEE
13 years 11 months ago
LSF mapping for voice conversion with very small training sets
To make voice conversion usable in practical applications, the number of training sentences should be minimized. With traditional Gaussian mixture model (GMM) based techniques sma...
Elina Helander, Jani Nurminen, Moncef Gabbouj
ICASSP
2010
IEEE
13 years 5 months ago
Non-parallel training for many-to-many eigenvoice conversion
This paper presents a novel training method of an eigenvoice Gaussian mixture model (EV-GMM) effectively using non-parallel data sets for many-to-many eigenvoice conversion, which...
Yamato Ohtani, Tomoki Toda, Hiroshi Saruwatari, Ki...
ICASSP
2011
IEEE
12 years 9 months ago
EM-style optimization of hidden conditional random fields for grapheme-to-phoneme conversion
We have recently proposed an EM-style algorithm to optimize log-linear models with hidden variables. In this paper, we use this algorithm to optimize a hidden conditional random ï...
Georg Heigold, Stefan Hahn, Patrick Lehnen, Herman...