ABSTRACT
Smart homes represent one of the principal points in the new ecosystem of the Internet of Things (IoT), both for the centrality of the home in the life of individuals and the significant potential concerning the diffusion of smart objects and innovative services. While IoT-oriented smart homes can revise how inhabitants interact with the domestic environment, each well-defined piece of technology necessitates precise network performance and distinct levels of security based on the sensitivity of the controlled system and the information it handles. This editorial presents a review of the papers accepted in the special issue. The issue has focused at obtaining high-quality papers aimed at solving well-known technical problems and challenges typical of IoT-oriented smart homes.
ABSTRACT
Model adaptation is a key technique that enables a modern automatic speech recognition (ASR) system to adjust its parameters, using a small amount of enrolment data, to the nuances in the speech spectrum due to microphone mismatch in the training and test data. In this brief, we investigate four different adaptation schemes for connectionist (also known as hybrid) ASR systems that learn microphone-specific hidden unit contributions, given some adaptation material. This solution is made possible adopting one of the following schemes: 1) the use of Hermite activation functions; 2) the introduction of bias and slope parameters in the sigmoid activation functions; 3) the injection of an amplitude parameter specific for each sigmoid unit; or 4) the combination of 2) and 3). Such a simple yet effective solution allows the adapted model to be stored in a small-sized storage space, a highly desirable property of adaptation algorithms for deep neural networks that are suitable for large-scale online deployment. Experimental results indicate that the investigated approaches reduce word error rates on the standard Spoke 6 task of the Wall Street Journal corpus compared with unadapted ASR systems. Moreover, the proposed adaptation schemes all perform better than simple multicondition training and comparable favorably against conventional linear regression-based approaches while using up to 15 orders of magnitude fewer parameters. The proposed adaptation strategies are also effective when a single adaptation sentence is available.