A mechanism for personalized Automatic Speech Recognition for less frequently spoken languages: the Greek case

Automatic Speech Recognition (ASR) has become increasingly popular since it significantly simplifies human-computer interaction, providing a more intuitive way of communication. Building an accurate, general-purpose ASR system is a challenging task that requires a lot of data and computing power. Especially for languages not widely spoken, such as Greek, the lack of adequately large speech datasets leads to the development of ASR systems adapted to a restricted corpus and/or for specific topics. When used in specific domains, these systems can be both accurate and fast, without the need for large datasets and extended training. An interesting application domain of such narrow-scope ASR systems is the development of personalized models that can be used for dictation. In the current work we present three personalization-via-adaptation modules, that can be integrated into any ASR/dictation system and increase its accuracy. The adaptation can be applied both on the language model (based on past text samples of the user) as well as on the acoustic model (using a set of user’s narrations). To provide more precise recommendations, clustering algorithms are applied and topic-specific language models are created. Also, heterogeneous adaptation methods are combined to provide recommendations to the user. Evaluation performed on a self-created database containing 746 corpora included in messaging applications and e-mails from the same user, demonstrates that the proposed approach can achieve better results than the vanilla existing Greek models.