A comparison of fusion techniques in mel-cepstral based speaker identification

Slomka, S.; Sridharan, Sridha; Chandran, Vinod

doi:10.21437/icslp.1998-236

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also the fundamental frequency has been used in addition with the cepstral vectors to improve recognition accuracy. In general, vector concatenation is termed as classifier input fusion [12].…”

Section: Introductionmentioning

confidence: 99%

“…In classifier output fusion, each individual data source is modeled separately, and the outputs of the individual classifier scores are combined to give the overall match score. For instance, output fusion of the cepstral and delta-cepstral features has been performed using VQ codebooks [14] and Gaussian mixture models [12] as the individual classifiers.…”

Section: Introductionmentioning

confidence: 99%

“…Slomka & al. [12] compared input and output fusion for the mel-cepstrum and corresponding delta features. They found out that the output fusion performed consistently better.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On the fusion of dissimilarity-based classifiers for speaker identification

Kinnunen

Hautamäki²,

Fränti³

2003

8th European Conference on Speech Communication and Technology (Eurospeech 2003)

View full text Add to dashboard Cite

In this work, we describe a speaker identification system that uses multiple supplementary information sources for computing a combined match score for the unknown speaker. Each speaker profile in the database consists of multiple feature vector sets that can vary in their scale, dimensionality, and the number of vectors. The evidence from a given feature set is weighted by its reliability that is set in a priori fashion. The confidence of the identification result is also estimated. The system is evaluated with a corpus of 110 Finnish speakers. The evaluated feature sets include mel-cepstrum, LPC-cepstrum, dynamic cepstrum, long-term averaged spectrum of /A/ vowel, and F0.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On the fusion of dissimilarity-based classifiers for speaker identification

Kinnunen

Hautamäki²,

Fränti³

2003

8th European Conference on Speech Communication and Technology (Eurospeech 2003)

View full text Add to dashboard Cite

show abstract

An overview of text-independent speaker recognition: From features to supervectors

Kinnunen¹,

Li²

2010

Speech Communication

1,224

706

View full text Add to dashboard Cite

This paper gives an overview of automatic speaker recognition technology, with an emphasis on text-independent recognition. Speaker recognition has been studied actively for several decades. We give an overview of both the classical and the state-of-the-art methods. We start with the fundamentals of automatic speaker recognition, concerning feature extraction and speaker modeling. We elaborate advanced computational techniques to address robustness and session variability. The recent progress from vectors towards supervectors opens up a new area of exploration and represents a technology trend. We also provide an overview of this recent development and discuss the evaluation methodology of speaker recognition systems. We conclude the paper with discussion on future directions.

show abstract

A comparison of fusion techniques in mel-cepstral based speaker identification

Cited by 2 publications

References 0 publications

On the fusion of dissimilarity-based classifiers for speaker identification

On the fusion of dissimilarity-based classifiers for speaker identification

An overview of text-independent speaker recognition: From features to supervectors

Contact Info

Product

Resources

About