Comparing data-driven and phonetic N-gram systems for text-independent speaker verification

Recognition of speaker identity based on modeling the streams produced by phonetic decoders (phonetic speaker recognition) has gained popularity during the past few years. Two of the major problems that arise when phone based systems are being developed are the possible mismatches between the development and evaluation data and the lack of transcribed databases. Data-driven segmentation techniques provide a potential solution to these problems because they do not use transcribed data and can easily be applied on development data minimizing the mismatches. In this paper we compare speaker recognition results using phonetic and data-driven decoders. To this end, we have compared the results obtained with two sets of speaker verification systems; the first one based on data-driven units and the second one on phonetic units. Results obtained on the NIST 2006 Speaker Recognition Evaluation data show that the data-driven approach is comparable to the phonetic one and that further improvements can be achieved by combining both approaches.