Sorry, you need to enable JavaScript to visit this website.

This paper addresses the task of Automatic Speech Recognition (ASR) with music in the background, where the accuracy of recognition may deteriorate significantly.
To improve the robustness of ASR in this task, e.g. for broadcast news transcription or subtitles creation, we adopt two approaches:
1) multi-condition training of the acoustic models and 2) denoising autoencoders followed by acoustic model training on the preprocessed data.
In the latter case, two types of autoencoders are considered: the fully connected and the convolutional network.