Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech

15 June 2022

Papers citing "Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech"

4 / 4 papers shown

Title
Zero-Shot vs. Few-Shot Multi-Speaker TTS Using Pre-trained Czech SpeechT5 Model Jan Lehecka Z. Hanzlícek J. Matousek Daniel Tihelka 32 0 0 24 Jul 2024
Transfer Learning of Transformer-based Speech Recognition Models from Czech to Slovak Jan Lehecka J. Psutka Josef Psutka 14 1 0 07 Jun 2023
Transformer-based encoder-encoder architecture for Spoken Term Detection J. Svec L. Smídl Jan Lehecka 11 0 0 02 Nov 2022
Multitask Detection of Speaker Changes, Overlapping Speech and Voice Activity Using wav2vec 2.0 Marie Kunesova Zbynek Zajíc SSL VLM 13 15 0 26 Oct 2022