Picture for Simon Berger

Simon Berger

Investigating the Effect of Label Topology and Training Criterion on ASR Performance and Alignment Quality

Add code
Jul 16, 2024
Viaarxiv icon

Mixture Encoder Supporting Continuous Speech Separation for Meeting Recognition

Add code
Sep 15, 2023
Viaarxiv icon

Mixture Encoder for Joint Speech Separation and Recognition

Add code
Jun 21, 2023
Viaarxiv icon

RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition

Add code
May 28, 2023
Viaarxiv icon

HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch

Add code
Oct 18, 2022
Figure 1 for HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch
Figure 2 for HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch
Figure 3 for HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch
Figure 4 for HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch
Viaarxiv icon

Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition

Add code
Nov 09, 2020
Figure 1 for Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition
Figure 2 for Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition
Figure 3 for Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition
Figure 4 for Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition
Viaarxiv icon