This paper introduces a new open-sourced Mandarin speech corpus, called DiDiSpeech.
Audio and Speech Processing
In this paper, we conduct a further study on MPC and focus on three important aspects: the effect of pre-training data speaking style, its extension on streaming model, and how to better transfer learned knowledge from pre-training stage to downstream tasks.
Speech recognition technologies are gaining enormous popularity in various industrial applications.
Code-switching speech recognition has attracted an increasing interest recently, but the need for expert linguistic knowledge has always been a big issue.