Speech processing technologies and telecommunications applications at NTT

Abstract

acomputer. When ANSER was first developed in 1981, the system This paper descnbes major research and development in speech had only voice response capability and could accept input only from recognition and synthesis technologies at N T r from the touch-tone telephones through DTMF signals Speech recognition US telecommunications applications viewpoint Technologies include added by the end of bat year, permitung system access through ordinary speaker-dependent. speaker-independent word recognition based on DP dial telephones Later. facsimile and modem access capabilities were matching. speaker-independent word spotting based on H h N , large added Figure 1 shows a typical ANSER system configuration for a vocabulary. speaker-independent continuous speech recogniuon based banking application ANSER systems are in place in more than 15 on HMM-LR and high-quality Japanese Text-to-Speech synthesis A cities across Japan, with all ANSER centers interconnccred by a daw commercial ANSER system that uses speech recognition and synthesis communicauons network Custoniers can access an ANSER center and technologies is also introduced obmn banking services for a small fee wherever they lire Speaker-independent speech recognition is particularly difficult through telephone lines because. in addiiion to variation, among speakers, telephone sets and lines cause varying amoun& of distoruon The System's 16-word kXiCOn COIlSiSts Of the 10 digits and six conuol words In Japanese A huge amount of telephone speech with a wide range of telephone-set and line vanatlOnS and speaker characterisucs was collected 10 form a speech database. The samples came from three regions of Japan and were generated by 15% male and female s e e r s ranging In age from 20 to 60 Yeus The basic idea for bocabulavindependent word recognilion based on DP matching was introduced Namely, each word 15 expressed as a sequence of phoneme [emplates 1.Introduction The "Multimedia Em" will Smn based on [he advent of B. ISDN and Under these cucumstances. the variou~ new services will uulize video. speech, text, data and other multimedia

Corporate Activities in Speech Recognition and Natural Language: Another "New Science"-Based Technology

“…There have been few commercial ASR telecommunications applications in Japan since the ANSER system was introduced for public use (Nitta, 1994;Sugamura et aL, 1994). 20 However, the long-term research of several non-computing companies (SONY, Nippondenso, etc.)…”