research
∙
04/22/2022
Efficient Training of Neural Transducer for Speech Recognition
As one of the most popular sequence-to-sequence modeling approaches for ...
share
research
∙
11/05/2021
Conformer-based Hybrid ASR System for Switchboard Dataset
The recently proposed conformer architecture has been successfully used ...
research
∙
10/18/2021
Automatic Learning of Subword Dependent Model Scales
To improve the performance of state-of-the-art automatic speech recognit...
research
∙
10/18/2021
Efficient Sequence Training of Attention Models using Approximative Recombination
Sequence discriminative training is a great tool to improve the performa...
research
∙
04/12/2021
Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models
Attention-based encoder-decoder (AED) models learn an implicit internal ...
research
∙
04/09/2021
Feature Replacement and Combination for Hybrid ASR Systems
Acoustic modeling of raw waveform and learning feature extractors as par...
research
∙
04/07/2021
Librispeech Transducer Model with Internal Language Model Prior Correction
We present our transducer model on Librispeech. We study variants to inc...
research
∙
05/20/2020
Early Stage LM Integration Using Local and Global Log-Linear Combination
Sequence-to-sequence models with an implicit alignment mechanism (e.g. a...
research
∙
04/02/2020
The RWTH ASR System for TED-LIUM Release 2: Improving Hybrid HMM with SpecAugment
We present a complete training pipeline to build a state-of-the-art hybr...
research
∙
07/01/2019
Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR
Sequence discriminative training criteria have long been a standard tool...
research
∙
05/08/2019