Language models for speech recognition tend to be brittle across domains, since their performance is vulnerable to changes in the genre or topic of the text on which they are trai...
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...
Abstract. The paper presents an implemented model for priming speech recognition, using contextual information about salient entities. The underlying hypothesis is that, in human-r...
Speaker recognition remains a challenging task under noisy conditions. Inspired by auditory perception, computational auditory scene analysis (CASA) typically segregates speech by...
Abstract. Systems for keyword and non-linguistic vocalization detection in conversational agent applications need to be robust with respect to background noise and different speak...