Audio-visual speech recognition in a Portuguese language based application

Pera, Vitor; Sa, F.; Afonso, Paulo; Ferreira, Ricardo

doi:10.1109/icit.2003.1290738

Cited by 6 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this method was influenced by light, shadow and beard. Lewis T W Pera V et al got lip area though eliminating the red color from the color of skin [26,27]. Lievin M et al used the differences of color between skin and lip, first transformed RGB space to space which color in lip area obviously enhanced, than to splitting lip area [28,29,30].…”

Section: A Lip Detection and Localizationmentioning

confidence: 99%

Review of Lip-Reading Recognition

Zheng¹,

Zhu²,

Li³

2014

2014 Seventh International Symposium on Computational Intelligence and Design

View full text Add to dashboard Cite

Lip-reading technology was introduced in this paper, including the development course, technical methods and application direction. Lip-reading technology mainly includes the lip detection and localization, feature extraction and recognition method and fusion method, the classification of the mouth and the corpus. This paper do a detailed comparative analysis for traditional methods and new technology, emphatically introduces the lip feature extraction.

show abstract

Section: A Lip Detection and Localizationmentioning

confidence: 99%

Review of Lip-Reading Recognition

Zheng¹,

Zhu²,

Li³

2014

2014 Seventh International Symposium on Computational Intelligence and Design

View full text Add to dashboard Cite

show abstract

“…Several papers concerning digit recognition are found in speech recognition literature [1,2], but few results have been published until now in the particular case of applications using the Portuguese language [3].…”

Section: Introductionmentioning

confidence: 99%

Digit recognition using wavelet and SVM in Brazilian Portuguese

Bresolin

Neto

Alsina

2008

2008 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

In this paper we used WPT (Wavelet Packet Transform) and neural classifier SVM (Support Vector Machine) to recognize spoken digits from 0 to 9 in Brazilian Portuguese. The main objective this work is to find out the Wavelet mother that better represents the speech signal in Brazilian Portuguese. The results obtained were compared with MFCC (Mel frequency cepstral coefficients). We carried out sixteen experiments with different Wavelets in dependentcase and four experiments in independent-case. The database was recorded in three months with 82 eighteen-toforty years old male speakers. The SVM was used as a classifier in a "one vs. all" strategy. Best results have been obtained using Wavelets Daubechies 5, Meyer and Coiflet 5. Finally, we used a neural network MLP (Multi Layer Perceptron) in order to improve the SVM results.

show abstract

“…The extraction of the ROI was a relatively easy task, given the nature of this application, with the user maintaining a quite steady position and a frontal image of the face being captured. The implemented approach uses an algorithm based on image symmetry properties [5].…”

Section: The Database Packagementioning

confidence: 99%

“…Therefore, the limited number of available audio-visual databases is not surprising. To the best of the authors' knowledge, before the LPFAV2 was created only one audio-visual database existed in the particular case of speech recognition applications supported by the Portuguese language [5]. Furthermore, the LPFAV2 is the first one that was specially designed for an application where the user has a specific motor impairment.…”

Section: Introductionmentioning

confidence: 99%

A New Multi-modal Database for Developing Speech Recognition Systems for an Assistive Technology Application

Moura

Freitas

Pera

2004

Text, Speech and Dialogue

View full text Add to dashboard Cite

Abstract. In this paper we report on the acquisition and content of a new database intended for developing audio-visual speech recognition systems. This database supports a speaker dependent continuous speech recognition task, based on a small vocabulary, and was captured in the European Portuguese language. Along with the collected multi-modal speech materials, the respective orthographic transcription and time-alignment files are supplied. The package also includes data on stochastic language models and the generative grammar associated to the collected spoken sentences. The application addressed by this database, which consists of voice control of a basic scientific calculator, has the particularity of being designed for a person with a specific motor impairment, namely muscular dystrophy. This specificity is a remarkable characteristic, given the lack of such kind of data resources for developing assistive systems based on audio-visual speech recognition technology.

show abstract

Audio-visual speech recognition in a Portuguese language based application

Cited by 6 publications

References 9 publications

Review of Lip-Reading Recognition

Review of Lip-Reading Recognition

Digit recognition using wavelet and SVM in Brazilian Portuguese

A New Multi-modal Database for Developing Speech Recognition Systems for an Assistive Technology Application

Contact Info

Product

Resources

About