Fernandez Diaz, MiguelGallardo Antolín, Ascensión2021-09-062022-11-012020-11Fernández-Díaz, M. & Gallardo-Antolín, A. (2020). An attention Long Short-Term Memory based system for automatic classification of speech intelligibility. Engineering Applications of Artificial Intelligence, 96, 103976.0952-1976https://hdl.handle.net/10016/33236Speech intelligibility can be degraded due to multiple factors, such as noisy environments, technical difficulties or biological conditions. This work is focused on the development of an automatic non-intrusive system for predicting the speech intelligibility level in this latter case. The main contribution of our research on this topic is the use of Long Short-Term Memory (LSTM) networks with log-mel spectrograms as input features for this purpose. In addition, this LSTM-based system is further enhanced by the incorporation of a simple attention mechanism that is able to determine the more relevant frames to this task. The proposed models are evaluated with the UA-Speech database that contains dysarthric speech with different degrees of severity. Results show that the attention LSTM architecture outperforms both, a reference Support Vector Machine (SVM)-based system with hand-crafted features and a LSTM-based system with Mean-Pooling.8eng© 2020 Elsevier Ltd.Atribución-NoComercial-SinDerivadas 3.0 EspañaSpeech intelligibilityDysarthriaLong Short-Term Memory (LSTM)Attention modelMachine learningresearch articleTelecomunicacioneshttps://doi.org/10.1016/j.engappai.2020.103976open access11039768Engineering Applications of Artificial Intelligence96AR/0000025407