When building a new spoken dialogue application, large amounts of domain specific data are required. This paper addresses the issue of generating in-domain training data when litt...
High-level spoken document analysis is required in many applications seeking access to the semantic content of audio data, such as information retrieval, machine translation or au...
Julien Fayolle, Fabienne Moreau, Christian Raymond...
Word discovery is the task of discovering and collecting occurrences of repeating words in the absence of prior acoustic and linguistic knowledge, or training material. The capabi...
Recognition of signs in sentences requires a training
set constructed out of signs found in continuous sentences.
Currently, this is done manually, which is a tedious process.
I...
Semantic role labeling (SRL) is an important module of spoken language understanding systems. This work extends the standard evaluation metrics for joint dependency parsing and SR...