Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approa...
Lukas Burget, Petr Schwarz, Mohit Agarwal, Pinar A...
We have applied two state-of-the-art speech synthesis techniques (unit selection and HMM-based synthesis) to the synthesis of emotional speech. A series of carefully designed perc...
Roberto Barra-Chicote, Junichi Yamagishi, Simon Ki...
This paper presents a new approach to language model construction, learning a language model not from text, but directly from continuous speech. A phoneme lattice is created using...
Graham Neubig, Masato Mimura, Shinsuke Mori, Tatsu...
Abstract--Independent vector analysis (IVA) is a method for separating convolutedly mixed signals that significantly reduces the occurrence of the well-known permutation problem in...
Alireza Masnadi-Shirazi, Wenyi Zhang, Bhaskar D. R...
Many of the kinds of language model used in speech understanding suffer from imperfect modeling of intra-sentential contextual influences. I argue that this problem can be address...