Speaker recognition apparatus and speaker recognition method to eliminate a trade-off relationship between phonological resolving performance and speaker resolving performance

1. A speaker recognition apparatus comprising:

means for obtaining a weighted vector distance, which is based on a first weight, between voice feature vectors of a first voice feature vector sequence produced from a voice of a speaker to be registered, for clustering the first voice feature vector sequence based on the obtained weighted vector distance, and for producing a codebook including a plurality of representative vectors;

means for storing the produced codebook;

means for obtaining a weighted quantization distance, which is based on a second weight, between corresponding ones of the plurality of representative vectors stored in the codebook and each voice feature vector of a second voice feature vector sequence produced from a voice of a speaker to be recognized, for quantizing each said voice feature vector of the second voice feature vector sequence based on the obtained weighted quantization distance, and for obtaining a weighted quantization distortion, which is based on a third weight which differs from the first weight and the second weight, between the corresponding ones of the plurality of representative vectors stored in the codebook and each said voice feature vector of the second voice feature vector sequence; and

means for executing speaker recognition based on the quantization distortion.

2. The speaker recognition apparatus according to claim 1 , wherein each of the first voice feature vector sequence and the second voice feature vector sequence is a M-order voice feature vector sequence;

wherein both the first weight of the weighted vector distance and the second weight of the weighted quantization distance are U K , where:

U K =1 (k≦N), 0 (k>N), and

N<M; and

wherein the third weight of the weighted distortion distance is V K , where:

V K =1 (k≦M).

3. The speaker recognition apparatus according to claim 1 , wherein each of the first voice feature vector sequence and the second voice feature vector sequence is a M-order voice feature vector sequence;

wherein both the first weight of the weighted vector distance and the second weight of the weighted quantization distance are U K , where:

U K =1 ( k≦M ); and

wherein the third weight of the weighted distortion distance is V K, where:

V K =1 /S K ( k≦M ),

and a dispersal value by every M-order is S K .

4. A speaker recognition method for a speaker recognition apparatus, the method comprising:

obtaining a weighted vector distance, which is based on a first weight, between voice feature vectors of a first voice feature vector sequence produced from a voice of a speaker to be registered, clustering the first voice feature vector sequence based on the obtained weighted vector distance, and producing a codebook including a plurality of representative vectors, by a speaker model production part of the apparatus;

storing the produced codebook in a storage section of the apparatus;

obtaining a weighted quantization distance, which is based on a second weight, between corresponding ones of the plurality of representative vectors stored in the codebook and each voice feature vector of a second voice feature vector sequence produced from a voice of a speaker to be recognized, quantizing each said voice feature vector of the second voice feature vector sequence based on the obtained weighted quantization distance, and obtaining a weighted quantization distortion, which is based on a third weight which differs from the first weight and the second weight, between the corresponding ones of the plurality of representative vectors stored in the codebook and each said voice feature vector of the second voice feature vector sequence, by a speaker distance calculation part of the apparatus; and

executing speaker recognition based on the obtained quantization distortion, by a recognition part of the apparatus.

5. A computer readable storage medium having a program stored thereon that is executable by a computer to cause the computer to perform a speaker recognition process comprising:

obtaining a weighted vector distance, which is based on a first weight, between voice feature vectors of a first voice feature vector sequence produced from a voice of a speaker to be registered, clustering the first voice feature vector sequence based on the obtained weighted vector distance, and producing a codebook including a plurality of representative vectors;

storing the produced codebook;

obtaining a weighted quantization distance, which is based on a second weight, between corresponding ones of the plurality of representative vectors stored in the codebook and each voice feature vector of a second voice feature vector sequence produced from a voice of a speaker to be recognized, quantizing each said voice feature vector of the second voice feature vector sequence based on the obtained weighted quantization distance, and obtaining a weighted quantization distortion, which is based on a third weight which differs from the first weight and the second weight, between the corresponding ones of the plurality of representative vectors stored in the codebook and each said voice feature vector of the second voice feature vector sequence; and

executing speaker recognition based on the obtained quantization distortion.