2021

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/2163

Browse

Filters

20212

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Speech Recognition

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationEmbargo
    E-Learning Platform for Hearing Impaired Students
    (2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Krishnamoorthy, N.; Raveendran, A.; Vadiveswaran, P.; Arulraj, S.R.; Manathunga, K.; Siriwardana, S.
    With the Spread of global pandemic Covid-19, the traditional education was transformed to online from traditional learning drastically. Hence the use of e-Learning platforms was increased. But this idea has issues with certain communities of people around the world. The hearing-impaired people have many issues with eLearning platforms because of their deficiency in hearing sound. Therefore, through this paper authors are introducing a learning platform for hearing impaired communities to aid in learning effectively. The proposed platform uses sign language to facilitate communication among students and tutors while providing sign language learning materials, practicing opportunities and Q&A sessions. The system has a low light enhancement module to enhance the videos uploaded by the tutor, module to convert the uploaded videos to American Sign Language and it also converts the questions asked via sign language to text.
  • Thumbnail Image
    PublicationEmbargo
    Digital Preservation and Noise Reduction using Machine Learning
    (2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Aravinda, K.P.; Sandeepa, K.G.H.; Sedara, V. V.; Chamodya, A.K.Y.L.; Dharmasena, T.; Abeygunawardhana, P.K.W.
    This paper proposes a digital preservation solution for Sinhala audios to conserve those as documents with noise reduction. The solution has implemented multiple noise reduction techniques as a pre-processing step to remove unwanted internal and external noises. A two-step, two-way noise reduction process is applied to produce clean audios based on Deep Convolutional Neural Network (DCNN) and adaptive filter-based techniques. This approach implements two separate noise reduction models for internal and external noises. After that, the speech recognition decoder recognizes the speech and converts it to a Unicode document by acoustic, language, and pronunciation models using extracted audio features from the denoised audio. Further, noise reduction models are decoupled from the preservation solution and exposed as a sub solution for multilingualism noise reduction, supporting English and Sinhala audios.