To achieve natural high quality synthesised speech in HMMbased speech synthesis, the effective modelling of complex acoustic and linguistic contexts is critical. Traditional appro...
When exposed to environmental noise, speakers adjust their speech production to maintain intelligible communication. This phenomenon, called Lombard effect (LE), is known to consi...
Update of acoustic and language models is vital to maintain performance of automatic speech recognition (ASR) systems. To alleviate efforts for updating models, we propose a "...
Yuya Akita, Masato Mimura, Graham Neubig, Tatsuya ...