research
∙
05/28/2023
RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition
Modern public ASR tools usually provide rich support for training variou...
share
research
∙
01/24/2022
Improving Factored Hybrid HMM Acoustic Modeling without State Tying
In this work, we show that a factored hybrid hidden Markov model (FH-HMM...
research
∙
04/06/2021
Towards Consistent Hybrid HMM Acoustic Modeling
High-performance hybrid automatic speech recognition (ASR) systems are o...
research
∙
05/15/2020
Context-Dependent Acoustic Modeling without Explicit Phone Clustering
Phoneme-based acoustic modeling of large vocabulary automatic speech rec...
research
∙
07/01/2019
LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoring
LSTM based language models are an important part of modern LVCSR systems...
research
∙
05/08/2019