Recent improvements of the SpeeD Romanian LVCSR system
Horia Cucu, Andi Buzo, Lucian Petrică, Dragoş Burileanu, Corneliu Burileanu · 2014
This paper presents the main improvements brought recently to the SpeeD automatic speech recognition system. Several aspects, such as speech and text resources acquisition, noise-robust speech features and feature transforms are discussed. All the updates in our ASR system are accompanied by experimental results illustrating significant improvements: between 30% and 35% relative WER reductions for various case studies (read/spontaneous speech, noisy/clean speech). In the last part of the paper, our ASR system is also compared with Google's ASR system and a brief analysis of the results is presented.