2017/03/24 by Mirco Ravanelli, Philémon Brakel, Ravanelli, Mirco +5
Computer Science · Engineering · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Indoor and Outdoor Localization Technologies #Machine Learning (cs.LG) #Speech Recognition and Synthesis #Speech and Audio Processing
paper · pdf · doi:10.48550/arxiv.1703.08471
openalex publication_date 2017/03/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04
Improving distant speech recognition is a crucial step towards flexible human-machine interfaces. Current technology, however, still exhibits a lack of robustness, especially when adverse acoustic conditions are met. Despite the significant progress made in the last years on both speech enhancement and speech recognition, one potential limitation of state-of-the-art technology lies in composing modules that are not well matched because they are not trained jointly. To address this concern, a promising approach consists in concatenating a speech enhancement and a speech recognition deep neural network and to jointly update their parameters as if they were within a single bigger network. Unfortunately, joint training can be difficult because the output distribution of the speech enhancement system may change substantially during the optimization procedure. The speech recognition module would have to deal with an input distribution that is non-stationary and unnormalized. To mitigate this issue, we propose a joint training approach based on a fully batch-normalized architecture. Experiments, conducted using different datasets, tasks and acoustic conditions, revealed that the proposed framework significantly overtakes other competitive solutions, especially in challenging environments.