+ Site Statistics
+ Search Articles
+ PDF Full Text Service
How our service works
Request PDF Full Text
+ Follow Us
Follow on Facebook
Follow on Twitter
Follow on LinkedIn
+ Subscribe to Site Feeds
Most Shared
PDF Full Text
+ Translate
+ Recently Requested

Metrics for vector quantization-based parametric speech enhancement and separation



Metrics for vector quantization-based parametric speech enhancement and separation



Journal of the Acoustical Society of America 133(5): 3062-3071



Speech enhancement and separation algorithms sometimes employ a two-stage processing scheme, wherein the signal is first mapped to an intermediate low-dimensional parametric description after which the parameters are mapped to vectors in codebooks trained on, for example, individual noise-free sources using a vector quantizer. To obtain accurate parameters, one must employ a good estimator in finding the parameters of the intermediate representation, like a maximum likelihood estimator. This leaves some unanswered questions, however, like what metrics to use in the subsequent vector quantization process and how to systematically derive them. This paper aims at answering these questions. Metrics for this are presented and derived, and their use is exemplified on a number of different signal models by deriving closed-form expressions. The metrics essentially take into account in the vector quantization process that some parameters may have been estimated more accurately than others and that there may be dependencies between the estimation errors.

Please choose payment method:






(PDF emailed within 0-6 h: $19.90)

Accession: 054361286

Download citation: RISBibTeXText

PMID: 23654409

DOI: 10.1121/1.4799004


Related references

Vector quantization of speech frames based on self-organizing maps. Advances in Experimental Medicine and Biology 657: 201-216, 2010

Designing syntactic pattern classifiers using vector quantization and parametric string editing. IEEE Transactions on Systems Man and Cybernetics. Part B Cybernetics 29(6): 881-888, 1999

Optimal vector quantization of speech spectral principal components. Journal of the Acoustical Society of America 71(Suppl. 1): S6, 1982

Model-Based receptor quantization analysis for PET parametric imaging. Conference Proceedings 6: 5908-5911, 2005

Divergence-based vector quantization. Neural Computation 23(5): 1343-1392, 2011

A generalized interpolative vector quantization method for jointly optimal quantization, interpolation, and binarization of text images. IEEE Transactions on Image Processing 9(7): 1272-1281, 2000

A very low bit rate video coder based on vector quantization. IEEE Transactions on Image Processing 5(2): 263-273, 1996

A virtual image cryptosystem based upon vector quantization. IEEE Transactions on Image Processing 7(10): 1485-1488, 1998

Window-based example selection in learning vector quantization. Neural Computation 22(11): 2924-2961, 2010

Still image coding based on vector quantization and fractal approximation. IEEE Transactions on Image Processing 5(4): 587-597, 1996

Beat-based ECG compression using gain-shape vector quantization. IEEE Transactions on Bio-Medical Engineering 52(11): 1882-1888, 2005

Texture Classification Using Local Pattern Based on Vector Quantization. IEEE Transactions on Image Processing 24(12): 5379-5388, 2015

Network based isolated digit recognition using vector quantization. Journal of the Acoustical Society of America 76(Suppl. 1): S46, 1984

A medical ultrasonic image compression method based on vector quantization. Zhongguo Yi Liao Qi Xie Za Zhi 21(3): 125-129, 1997

Fractal image compression based on Delaunay triangulation and vector quantization. IEEE Transactions on Image Processing 5(2): 338-346, 1996