An approach to text-independent speaker recognition with short utterances

Li, K.; Wrench, Edwin H.

doi:10.1109/icassp.1983.1172258

Cited by 37 publications

(10 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As early as 1983, researchers from ITT Defense Communication Division have mentioned that for text-independent speaker recognition, both the training and test processes need to have an adequate speech data in order for the accuracy of modeling and recognition. Experimental results showed that the system was able to identify 11 speakers with 96%, 87% and 79% accuracy with test utterance durations of 10, 5 and 3 seconds, respectively [97].…”

Section: E Personalizationmentioning

confidence: 99%

An overview of robustness related issues in speaker recognition

Zheng¹,

Jin

Li³

et al. 2014

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

View full text Add to dashboard Cite

Speaker recognition technologies have been improved rapidly in recent years. However, critical robustness issues need to be addressed when they are applied in practical situations. This paper provides an overview of technologies dealing with robustness related issues in automatic speaker recognition. We first categorize the robustness issues into three categories, including environment-related, speaker-related and application-oriented issues. For each category, we then describe the current hot topics, existing technologies, and potential research focuses in the future.I.

show abstract

Section: E Personalizationmentioning

confidence: 99%

An overview of robustness related issues in speaker recognition

Zheng¹,

Jin

Li³

et al. 2014

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

View full text Add to dashboard Cite

show abstract

“…VQ can also be used for speaker recognition using a small VQ codebook consisting of highly representative speakerspecific feature vectors [29], [41], [63]. To differentiate between two speakers, training utterances from the two speakers are used to train two separate codebooks.…”

Section: Related Work In Speech Processingmentioning

confidence: 99%

Using vector quantization for image processing

Cosman¹,

Oehler²,

Riskin

et al. 1993

Proc. IEEE

View full text Add to dashboard Cite

Image compression is the process of reducing the number of bits required to represent an image. Vector quantization, the mapping of pixel intensiry vectors into binary vectors indexing a limited number of possible reproductions, is a popular image compression algorithm. Compression has traditionally been done with little regard for image processing operations that may precede or follow the compression step. Recent work has used vector quantization both to simplify image processing tasks-such as enhancement, classification, halftoning, and edge detectio-nd to reduce the computational complexiry by performing them simultaneously with the compression. After briefly reviewing the fundamental ideas of vector quantization, we present a survey of vector quantization algorithms that perform image processing.

show abstract

“…Earlier classification methods comprise use of the Euclidean distance between the features of a test signal and a reference utterance to measure the similarity, hence classification of the speech signal [7]. In [8] a VQ (vector quantization)-based classifier for handling text-independent speaker recognition problems with short utterance was discussed. In [9], the discrete hidden Markov model was augmented with temporal information for VQ to utilize the transition probabilities between states for speaker recognition.…”

Section: Introductionmentioning

confidence: 99%

Text-dependent Speaker Recognition using Wavelets and Neural Networks

Lim

Woo

2006

Soft Comput

View full text Add to dashboard Cite

An intelligent system for text-dependent speaker recognition is proposed in this paper. The system consists of a wavelet-based module as the feature extractor of speech signals and a neural-network-based module as the signal classifier. The Daubechies wavelet is employed to filter and compress the speech signals. The fuzzy ARTMAP (FAM) neural network is used to classify the processed signals. A series of experiments on text-dependent gender and speaker recognition are conducted to assess the effectiveness of the proposed system using a collection of vowel signals from 100 speakers. A variety of operating strategies for improving the FAM performance are examined and compared. The experimental results are analyzed and discussed.

show abstract

An approach to text-independent speaker recognition with short utterances

Cited by 37 publications

References 3 publications

An overview of robustness related issues in speaker recognition

An overview of robustness related issues in speaker recognition

Using vector quantization for image processing

Text-dependent Speaker Recognition using Wavelets and Neural Networks

Contact Info

Product

Resources

About