Augmenting standard speech recognition features with energy gravity centres

Mori, Renato De; Moisa, L.; Gemello, Roberto; Mana, Franco; Albesano, D.

doi:10.1006/csla.2001.0171

Cited by 4 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several published researches of using zero-crossing for speech processing [1], [2], [3], [4], [5]. In [1] are described possibilities of the spectral analysis based on zero-crossing.…”

Section: Feature Extractionmentioning

confidence: 99%

An audio stream classification and optimal segmentation for multimedia applications

Biatov¹,

Koehler²

2003

Proceedings of the Eleventh ACM International Conference on Multimedia

View full text Add to dashboard Cite

In this paper we investigate on-line zero-crossing based audio stream segmentation and classification into speech and other segments. We consider such segments as applause, noise of the auditorium, and silence. We demonstrate that the features extracted from zero-crossing are stable and valid to be used for speech and other signal discrimination and classification and don't require large amount of data for the training. We describe the optimal segmentation of unlimited audio signals using results of the frames classification. We demonstrate that using optimal segmentation is better than using traditional sliding window technique.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

An audio stream classification and optimal segmentation for multimedia applications

Biatov¹,

Koehler²

2003

Proceedings of the Eleventh ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Other approaches attempt to model spectral peaks rather than looking for resonances in the signal. These representations of spectral peaks have demonstrated a slight improvement in recognition performance when combined with MFCC systems (De Mori et al 2001;Weber et al 2001;Stuttle and Gales 2002).…”

Section: Introductionmentioning

confidence: 99%

Combining formant frequency based on variable order LPC coding with acoustic features for TIMIT phone recognition

Messaoud

Hamida

2011

Int J Speech Technol

View full text Add to dashboard Cite

Combination of multiple acoustic features has great potential to improve Automatic Speech Recognition (ASR) accuracy. Our contribution in this research was to investigate one novel method when using voiced formants' features in combination with standard MFCC features in order to enhance TIMIT phone recognition. These voiced features provide accurate formants frequencies using a Variable Order LPC Coding (VO-LPC) algorithm that was combined with continuity constraints. The overall estimating formants were concatenated with MFCC features when a voiced frame could be detected. For feature-level combination, Heteroscedastic Linear Discriminant Analysis (HLDA) based approach had been used successfully to find an optimal linear combination of successive vectors of a single feature stream.A series of experiments on phone recognition speakerindependent continuous-speech had been carried out using a subset of the large read-speech TIMIT phone corpus. Hidden Markov Model Toolkit (HTK) was also used throughout all carried experiments. Using such feature level combination, optimized mixture splitting and a bigram language model, a detailed analysis on this combination performance was discussed for Context-Independent (CI) and ContextDependent (CD) Hidden Markov Models (HMM). Experimental results from our proposed procedure showed that phone error rate was successfully decreased by about 3%. At phonetic level group, an increase of 8% and of 10% was observed respectively for vowel and liquid group. These results proved clear phone enhancement regarding existing state of the art.

show abstract

Constructing accurate and robust HMM/GMM models for an Arabic speech recognition system

Khelifa

Elhadj

Yousfi

et al. 2017

Int J Speech Technol

View full text Add to dashboard Cite

Augmenting standard speech recognition features with energy gravity centres

Cited by 4 publications

References 12 publications

An audio stream classification and optimal segmentation for multimedia applications

An audio stream classification and optimal segmentation for multimedia applications

Combining formant frequency based on variable order LPC coding with acoustic features for TIMIT phone recognition

Constructing accurate and robust HMM/GMM models for an Arabic speech recognition system

Contact Info

Product

Resources

About