A neural net acoustic phonetic feature extractor based on wavelets

Davenport, M.R.; Garudadri, Harinath

doi:10.1109/pacrim.1991.160774

Cited by 7 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The WT has been applied widely in different speech analysis problems [16,8,9,7,3]. Scalograms produced by WT and Spectrograms by STFT have been visually compared [6,11,12,9,1].…”

Section: Introductionmentioning

confidence: 99%

The use of wavelet transforms in phoneme recognition

Tan

Fu²,

Spray³

et al.

Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96

View full text Add to dashboard Cite

This study investigates the usefulness of wavelet transforms in phoneme recognition. Both discrete wavelet transforms (DWT) and sampled continuous wavelet transforms (SCWT) are tested. The wavelet transform is used as a part of the front-end processor which extracts feature vectors for a speakerindependent HMM-based phoneme recognizer. The results are evaluated on a portion of TIMIT corpus consisting of 30293 phoneme tokens for training and 14489 phoneme tokens for testing. The test results suggest that SCWT gives considerably better recognition rate than DWT. On the other hand, the improvement of SCWT over Mel-scale cepstral coecients appears to be marginal.

show abstract

“…The WT has been applied widely in different speech analysis problems [16,8,9,7,3]. Scalograms produced by WT and Spectrograms by STFT have been visually compared [6,11,12,9,1].…”

Section: Introductionmentioning

confidence: 99%

The use of wavelet transforms in phoneme recognition

Tan

Fu²,

Spray³

et al.

Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96

View full text Add to dashboard Cite

show abstract

“…By the time the late seventy's, because of the large-scale use of integrated circuit and the rapid progress of computer related technologies, the remote control technology was developed quickly. In the earliest remote wireless control equipment, it is a signal transmission through electromagnetic wave, however because the electromagnetic wave is very easy to form interference, so its transmission will be improved step by step by ultrasonic and infrared medium for signal [3]. However, the present infrared light can also directly through the information to be modulated transmission corresponding, and the infrared remote control technology has rapid progress and developed stage, which also make home appliances and other electronic field that has application and popularization of the broader [4].…”

Section: Introductionmentioning

confidence: 99%

Remote Access and Control System Based on Infrared Communication Technology

Jiang¹

2013

AMM

View full text Add to dashboard Cite

With the development of world science and technology, people's quality of life and living standard is also improving gradually, so the technology of remote access and control system will be born. The household appliances are carried out the remote access based on infrared communication technology, to construct the infrared communication coding protocol procedures, it can pass through the procedures to achieve the related functions of various electrical appliances with the organic coordination, in order to remote access for the household appliances. At the same time through the timing function of the infrared communication technology, it can be form a complete access and the control system, and can be the formation of the received infrared communication and emission flow diagram, in order to achieve the largest household appliance function and use, effectively guide people better infrared communication technology to be widely and effectively used.

show abstract

“…The wavelet transform (WT) theory provides an alternative tool for short time analysis of quasi stationary signal, such as speech, as opposed to the traditional short-time Fourier transform (STFT). The WT has been applied widely in different speech analysis problems [16,8,9,7,3]. Scalograms produced by WT and Spectrograms by STFT have been visually compared [6,11,12,9,1].…”

Section: Introductionmentioning

confidence: 99%