Total Voice Speaker Verification.

摘要

The objective of this resarch has been to develop a robust speaker-independent, connected digit-sequence recognition capability as the front-end for a speaker verification(voice authentication) program and to install and demonstrate that capability on the Base and Installation Security System Advanced Development Model for speaker verification located at RADC. In such a system, the correct digit sequence recognition provides the user identification of the claimed identity. Verification is then performed on the same speech data. This total-voice system must recognize connected digits independent of speaker with high reliability. Two sequence constraints aid recognition: two parity checks must be satisfied, and difficult digit pairs were disallowed. A further sequence constraint added to aid verification was that all digits must be different. The selected constraints yield 320 possible sequences. The speech processing strategy features highly reliable time registration and accommodates multiple concurrent hypotheses at various processing levels. Basic to robust speaker-independent recognition is the existence of a set of reference patterns capable of allowing for the speaker's sex and dialect. Rather than arbitrary segmentation of the design data to produce reference patterns, a hierarchical clustering algorithm was used, followed by an iterative optimization procedure.