Combining Visual and Acoustic Modalities to Ease Speech Recognition by Hearing Impaired People

Dalka P, Kostek B. Combining Visual and Acoustic Modalities to Ease Speech Recognition by Hearing Impaired People. In: AES Convention 118. Audio Engineering Society; 2005. Paper 6462. Available from: https://aes.org/publications/elibrary-page/?id=13178

@inproceedings{Dalka2005_13178,
  author = {Dalka, Piotr and Kostek, Bozena},
  title = {{Combining Visual and Acoustic Modalities to Ease Speech Recognition by Hearing Impaired People}},
  booktitle = {AES Convention 118},
  note = {Paper 6462},
  year = {2005},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=13178}
}

TY  - CPAPER
TI  - Combining Visual and Acoustic Modalities to Ease Speech Recognition by Hearing Impaired People
AU  - Dalka, Piotr
AU  - Kostek, Bozena
T2  - AES Convention 118
M1  - Paper 6462
PY  - 2005
DA  - 2005/05/06
UR  - https://aes.org/publications/elibrary-page/?id=13178
PB  - Audio Engineering Society
LA  - en
AB  - The aim of the research work presented is to show a system that facilitates speech training for hearing impaired people. The system engineered combines both visual and acoustic speech data acquisition and analysis modules. The Active Shape Model method is used for extracting visual speech features from the shape and movement of the lips. The acoustic features extraction involves mel-cepstral analysis. Artificial Neural Networks are utilized as the classifier, feature vectors extracted combine both modalities of the human speech. Additional experiments with the degraded acoustic and/or visual information are carried out in order to test the system robustness against various distortions affecting the signals.
ER  -