Nonuniform normalization of formant data

Intrinsic-cum-extrinsic normalization of formant data of vowels

Using a known speaker-intrinsic normalization procedure, formant data are scaled by the reciprocal of the geometric mean of the first three formant frequencies. This reduces the influence of the talker but results in a distorted vowel space. The proposed speaker-extrinsic procedure re-scales the normalized values by the mean formant values of vowels. When tested on the formant data of vowels pu...

Comparing Vowel Formant Normalization Methods

Results from a large-scale comparative study of vowel formant normalization methods are presented. Effectiveness of methods was evaluated by their ability to improve the equalization and alignment of speaker vowel spaces over raw Hertz measurements. Vowel-intrinsic methods performed poorly, while vowel-extrinsic, formant-intrinsic methods performed the best overall.

cDNA Microarray Data Normalization

Vocal Tract Normalization Based on Formant Positions

This paper presents our initial results in a new approach to vocal tract normalization (VTN). In experiments based on continuous automatic speech recognition (ASR) the VTN procedure is in general carried out in both training and test phase. In the training phase it is used to obtain speaker independent acoustic models of phones. In the test phase it is used to convert input observations into ob...

Speaker normalization through formant-based warping of the frequency scale

Speaker-dependent automatic speech recognition systems are known to outperform speaker-independent systems when enough training data are available to model acoustical variability among speakers. Speaker normalization techniques modify the spectral representation of incoming speech waveforms in an attempt to reduce variability between speakers. Recent successful speaker normalization algorithms ...