5 citations · 13 across the 8 of their papers we have counts for
8 papers
Zero-Shot vs. Few-Shot Multi-Speaker TTS Using Pre-trained Czech SpeechT5 Model
Jan Lehečka, Zdeněk Hanzlíček, Jindřich Matoušek +1
In this paper, we experimented with the SpeechT5 model pre-trained on large-scale datasets. We pre-trained the foundation model from scratch and fine-tuned it on a large-scale robu…
A Comparative Analysis of Bilingual and Trilingual Wav2Vec Models for Automatic Speech Recognition in Multilingual Oral History Archives
Jan Lehečka, Josef V. Psutka, Luboš Šmídl +2
In this paper, we are comparing monolingual Wav2Vec 2.0 models with various multilingual models to see whether we could improve speech recognition performance on a unique oral hist…
Speech Technology Services for Oral History Research
Christoph Draxler, Henk van den Heuvel, Arjan van Hessen +2
Oral history is about oral sources of witnesses and commentors on historical events. Speech technology is an important instrument to process such recordings in order to obtain tran…
Transfer Learning of Transformer-based Speech Recognition Models from Czech to Slovak
Jan Lehečka, Josef V. Psutka, Josef Psutka
In this paper, we are comparing several methods of training the Slovak speech recognition models based on the Transformers architecture. Specifically, we are exploring the approach…
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…
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…
Transformer-based Automatic Speech Recognition of Formal and Colloquial Czech in MALACH Project
Jan Lehečka, Josef V. Psutka, Josef Psutka
Czech is a very specific language due to its large differences between the formal and the colloquial form of speech. While the formal (written) form is used mainly in official docu…
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…