Speech activated telephony email reader (SATER) based on speaker verification and text-to-speech conversion

A speech activated telephony email reader (SATER) is proposed. SATER is an integrated system combining speaker verification, network, and text-to-speech conversion. A registered user can activate and listen to his own email through a wired/wireless telephone. In the speaker verification subsystem, a time-varying and speaker-dependent verification phrase is adopted. The speaker's password is used to generate the verification phrases for that speaker. A hidden Markov Model with states of a variable number is used to model each verification phrase. In the text-to-speech (TTS) subsystem, a prosody modification approach is proposed on the basis of word units. Appropriate word prosodic patterns in a sentence are selected from a word prosody database using linguistic features. This system has been tested on 20 subjects. In the speaker verification test, at 1.5% false rejection, the verification system resulted in 0.5% false acceptance. The results for the TTS conversion system indicated that the average correct rate was 95.7% for intelligibility, and that the mean opinion score (MOS) was 3.4 for naturalness.