7 citations · 13 across the 4 of their papers we have counts for
4 papers
Transformer-based encoder-encoder architecture for Spoken Term Detection
Jan Švec, Luboš Šmídl, Jan Lehečka
The paper presents a method for spoken term detection based on the Transformer architecture. We propose the encoder-encoder architecture employing two BERT-like encoders with addit…
Spoken Term Detection and Relevance Score Estimation using Dot-Product of Pronunciation Embeddings
Jan Švec, Luboš Šmídl, Josef V. Psutka +1
The paper describes a novel approach to Spoken Term Detection (STD) in large spoken archives using deep LSTM networks. The work is based on the previous approach of using Siamese n…
Deep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizer
Jan Švec, Jan Lehečka, Luboš Šmídl
In recent years, the standard hybrid DNN-HMM speech recognizers are outperformed by the end-to-end speech recognition systems. One of the very promising approaches is the grapheme…
Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech
Jan Lehečka, Jan Švec, Aleš Pražák +1
In this paper, we present our progress in pretraining Czech monolingual audio transformers from a large dataset containing more than 80 thousand hours of unlabeled speech, and subs…