Password-dependent speaker verification using quantized acoustic trajectories

Speaker verification requires either two steps (identity claim and verification) or the use of speech recognition to determine the password phrase. The single step method using speech recognition is textand language-dependent. We describe a novel single-step method based on Gaussian mixture models and quantized acoustic trajectories that does not use any linguistic knowledge and is thus textand languageindependent. Although a two-step process can be more accurate, our approach is significantly better than speaker identification and is more convenient than a two-step process.