This paper describes our participation in the TREC-9 Spoken Document Retrieval (SDR) track. The THISL SDR system consists of a realtime version of a hybrid connectionist/HMM large...
Neural network language models (NNLM) have become an increasingly popular choice for large vocabulary continuous speech recognition (LVCSR) tasks, due to their inherent generalisa...
Junho Park, Xunying Liu, Mark J. F. Gales, Philip ...
Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid...
Carolina Parada, Mark Dredze, Abhinav Sethy, Ariya...
This paper presents a method for rescoring the speech recognition lattices on-the-fly to increase the word accuracy while preserving low latency of a real-time speech recognition ...
This paper addresses selecting between candidate pronunciations for out-of-vocabulary words in speech processing tasks. We introduce a simple, unsupervised method that outperforms...
Christopher M. White, Abhinav Sethy, Bhuvana Ramab...