A frequency warping approach to speaker normalization

  title={A frequency warping approach to speaker normalization},
  author={Li Lee and Richard C. Rose},
  journal={IEEE Trans. Speech and Audio Processing},
In an effort to reduce the degradation in speech recognition performance caused by variation in vocal tract shape among speakers, a frequency warping approach to speaker normalization is investigated. A set of low complexity, maximum likelihood based frequency warping procedures have been applied to speaker normalization for a telephone based connected digit recognition task. This paper presents an efficient means for estimating a linear frequency warping factor and a simple mechanism for… CONTINUE READING
Highly Influential
This paper has highly influenced 41 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 297 citations. REVIEW CITATIONS

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • The results have shown that frequency warping is consistently able to reduce word error rate by 20% even for very short utterances.


Publications citing this paper.
Showing 1-10 of 206 extracted citations

VTLN-warped Gaussian posteriorgram for QbE-STD

2017 25th European Signal Processing Conference (EUSIPCO) • 2017
View 5 Excerpts
Highly Influenced

Data augmentation for deep convolutional neural network acoustic modeling

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2015
View 4 Excerpts
Highly Influenced

298 Citations

Citations per Year
Semantic Scholar estimates that this publication has 298 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 10 references

Dragon systems’ 1994 large vocabulary continuous speech recognizer

R. Roth
inProc. Spoken Language Systems Technology Workshop,1995. • 1995
View 2 Excerpts

Experiments in vocal tract normalization

A. Andreou, T. Kamm, J. Cohen
Proc. CAIP Workshop: Frontiers in Speech Recognition II, 1994. • 1994
View 1 Excerpt

Long-term feature averaging for speaker recognition

J. D. Markel, B. T. Oshika, A. H. Gray, Jr.
IEEE Trans. Acoust., Speech, Signal Processing,vol. ASSP-25, pp. 330–337, Aug. 1977. • 1977
View 1 Excerpt

Non-uniform vowel normalization

G. Fant
Speech Transmiss. Lab. Rep., Royal Inst. Technol., Stockholm, Sweden, 1975, vols. 2/3, pp. 1–19. • 1975
View 1 Excerpt

Speaker hierarchical clustering for improving speaker independent HMM word recognition

L. Mathan, L. Miclet
Proc. ICASSP 90, pp. 149–152.
View 1 Excerpt

Similar Papers

Loading similar papers…