This article reviews recent literature investigating speech variation in production and
comprehension during spoken language communication between humans and devices …

This study examined how speaking style and guise influence the intelligibility of text-to-
speech (TTS) and naturally produced human voices. Results showed that TTS voices were …

We have been investigating rakugo speech synthesis as a challenging example of speech
synthesis that entertains audiences. Rakugo is a traditional Japanese form of verbal …

We have been working on constructing rakugo speech synthesis as a challenging example
of speech synthesis that entertains audiences. Rakugo is a traditional Japanese form of …

Prosody is a key component in human spoken communication, signalling emotion, attitude,
information structure, intention, and other communicative functions through perceived …

When intelligent voice-based assistants (VBAs) present news, they simultaneously act as
interlocutors and intermediaries, enabling direct and mediated communication. Hence, this …

Recurrent neural networks (RNNs) form a significant proportion of data center deep learning
inference (29%[1]). This includes workloads like machine translation, speech synthesis and …

Abstract (EN) When intelligent voice-based assistants (VBAs) present news, they
simultaneously act as interlocutors and intermediaries, enabling direct and mediated …

Conventional speech synthesis research has focused on transferring information which the
speech should have, such as content and speakers' emotions, personality, intention …

We have been working on building rakugo speech synthesis as a challenging example of
speech synthesis that entertains audiences. Rakugo is a traditional Japanese form of verbal …