Skip to main content
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
    Length: 00:08:31
11 Jun 2021

Building a high quality automatic speech recognition (ASR) system with limited training data has been a challenging task particularly for a narrow target population. Open-sourced ASR systems, trained on sufficient data from adults, are susceptible on seniors’ speech due to acoustic mismatch between adults and seniors. With 12 hours of training data, we attempt to develop an ASR system for socially isolated seniors (80+ years old) with possible cognitive impairments. We experimentally identify that ASR for the adult population performs poorly on our target population and transfer learning (TL) can boost the system’s performance. Standing on the fundamental idea of TL, tuning model parameters, we further improve the system by leveraging the attention mechanism to utilize the model’s intermediate information. Utilizing our intuitive conditional-independent attention mechanism, our optimal model achieves $1.58\%$ absolute improvements over the TL model.

Chairs:
Shinji Watanabe

Value-Added Bundle(s) Including this Product

More Like This