A recent approach to speaker identification is based on personalised codebooks. The algorithm compares incoming test features with a set of N codebooks, one for each valid member of the user population, and the codebook which gives rise to the smallest accumulated distance for the full test feature sequence is assumed to identify the speaker. Results from this inherently text-independent approach have highlighted the performance variations for different test utterances: the spoken digit 'nine' is good, while 'six' is bad. This observation has lead to the idea of classifying speech, via a text and speaker-independent codebook, according to empirical discriminating properties in the recognition task. Such a classifier is developed here, and experimental results show that 10% or more of speech acts as little more than noise, interfering in the task of speaker recognition.