This paper first describes recent trends of ASR and TTS telecommunicat
ions applications in Japan. ASR applications focus on public services
such as operator automation, operator assistance, voice-activated info
rmation retrieval, and voice dialing. Major TTS applications include i
nformation service by voice and e-mail reading. The usage of ASR and T
TS functions is expected to dramatically increase in the near future w
ith the penetration of handy and mobile telephone terminals; hot topic
s are text broadcasting and digital communication. Secondly this paper
describes NTT's experimental interactive system featuring (1) highly
accurate speaker independent and large vocabulary speech recognition b
ased on context-dependent accurate acoustic phoneme HMM models trained
with speech data from more than 10,000 speakers collected over teleph
one network, (2) high quality text-to-speech synthesis that generates
speech by concatenating triphone-context-dependent waveform segments,
(3) software-based configuration that requires no special hardware exc
ept a PC equipped with a sound board and a voice modem, and (4) easy a
nd rapid prototyping which enables the developer to build a system by
writing some types of service scenarios. (C) 1997 Elsevier Science B.V
.