Alexander Gerstenberger — accepted AI-conference papers

2022

Conformer-Based Hybrid ASR System For Switchboard Dataset

Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher, Wilfried Michel, Alexander Gerstenberger, Ralf Schlüter +1

ICASSP 2022accepted

The recently proposed conformer architecture has been successfully used for end-to-end automatic speech recognition (ASR) architectures achieving state-of-the-art performance on different datasets. To our best knowledge, the impact of using conformer acoustic model for hybrid ASR is not investigated…

Cited by 0 Source ↗Scholar ↗

2020

Domain Robust, Fast, and Compact Neural Language Models

Alexander Gerstenberger, Kazuki Irie, Pavel Golik, Eugen Beck, Hermann Ney

ICASSP 2020accepted

Despite advances in neural language modeling, obtaining a good model on a large scale multi-domain dataset still remains a difficult task. We propose training methods for building neural language models for such a task, which are not only domain robust, but reasonable in model size and fast for eval…

Cited by 7 Source ↗Scholar ↗

2020

How Much Self-Attention Do We Need? Trading Attention for Feed-Forward Layers

Kazuki Irie, Alexander Gerstenberger, Ralf Schlüter, Hermann Ney

ICASSP 2020accepted

We propose simple architectural modifications in the standard Transformer with the goal to reduce its total state size (defined as the number of self-attention layers times the sum of the key and value dimensions, times position) without loss of performance. Large scale Transformer language models h…

Cited by 0 Source ↗Scholar ↗