Analysis of speaker variability.

  title={Analysis of speaker variability.},
  author={Chao Huang and Tao Chen and Stan Z. Li and Eric Chang and Jian-Lai Zhou},
Analysis and modeling of speaker variability, such as gender, accent, age, speech rate, and phones realizations, are important issues in speech recognition. It is known that existing feature representations describing speaker variations can be of very high dimension. In this paper, we introduce two powerful multivariate statistical analysis methods, namely, principal component analysis (PCA) and independent component analysis (ICA), as tools for analysis of such variability and extraction of… CONTINUE READING
Highly Cited
This paper has 62 citations. REVIEW CITATIONS

From This Paper

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

Key Quantitative Results

  • Using 2dimensional ICA representation, we achieved about 6.1% and 13.3% error rate in gender and accent classification, respectively, for 980 speakers.


Publications citing this paper.
Showing 1-10 of 43 extracted citations

Foreign English Accent Classification Using Deep Belief Networks

2018 IEEE 12th International Conference on Semantic Computing (ICSC) • 2018

A Hierarchical Framework for Accent Based Writer Identification

2014 11th IAPR International Workshop on Document Analysis Systems • 2014
View 1 Excerpt

An overview of robustness related issues in speaker recognition

Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific • 2014
View 1 Excerpt

62 Citations

Citations per Year
Semantic Scholar estimates that this publication has 62 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-7 of 7 references

Rapid speaker adaptation in eigenvoice space

IEEE Trans. Speech and Audio Processing • 2000
View 4 Excerpts
Highly Influenced

Understanding and adapting to speaker variability using correlation-based principal component analysis

Z. H. Hu
Dissertation of OGI. Oct • 1999
View 4 Excerpts
Highly Influenced

Analysis of a complex of statistical variables into principle components

H. Hotellings
J. Educ. Psychol., • 1933
View 1 Excerpt

Similar Papers

Loading similar papers…