Timo Lohrenz

According to our database, Timo Lohrenz authored at least 17 papers between 2016 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2023

An Efficient and Noise-Robust Audiovisual Encoder for Audiovisual Speech Recognition.

Zhengyang Li, Chenwei Liang, Timo Lohrenz, Marvin Sach, Björn Möller, Tim Fingscheidt

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Relaxed Attention for Transformer Models.

Timo Lohrenz, Björn Möller, Zhengyang Li, Tim Fingscheidt

Proceedings of the International Joint Conference on Neural Networks, 2023

Parameter-Efficient Cross-Language Transfer Learning for a Language-Modular Audiovisual Speech Recognition.

Zhengyang Li, Thomas Graave, Jing Liu, Timo Lohrenz, Siegfried Kunzmann, Tim Fingscheidt

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

2022

Transformer-Based Lip-Reading with Regularized Dropout and Relaxed Attention.

Zhengyang Li, Timo Lohrenz, Matthias Dunkelberg, Tim Fingscheidt

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

2021

Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition.

Timo Lohrenz, Zhengyang Li, Tim Fingscheidt

Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

A New DCASE 2017 Rare Sound Event Detection Benchmark Under Equal Training Data: CRNN With Multi-Width Kernels.

Jan Baumann, Patrick Meyer, Timo Lohrenz, Alexander Roy, Michael Papendieck, Tim Fingscheidt

Proceedings of the IEEE International Conference on Acoustics, 2021

Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition.

Timo Lohrenz, Patrick Schwarz, Zhengyang Li, Tim Fingscheidt

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2021

Multi-Head Fusion Attention for Transformer-Based End-to-End Automatic Speech Recognition.

Timo Lohrenz, Patrick Schwarz, Zhengyang Li, Tim Fingscheidt

Proceedings of the 14th ITG Conference on Speech Communication, online, September 29, 2021

2020

BLSTM-Driven Stream Fusion for Automatic Speech Recognition: Novel Methods and a Multi-Size Window Fusion Example.

Timo Lohrenz, Tim Fingscheidt

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

Beyond the Dcase 2017 Challenge on Rare Sound Event Detection: A Proposal for a More Realistic Training and Test Framework.

Jan Baumann, Timo Lohrenz, Alexander Roy, Tim Fingscheidt

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

On Temporal Context Information for Hybrid BLSTM-Based Phoneme Recognition.

Timo Lohrenz, Maximilian Strake, Tim Fingscheidt

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019

2018

Densenet Blstm for Acoustic Modeling in Robust ASR.

Maximilian Strake, Pascal Behr, Timo Lohrenz, Tim Fingscheidt

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

A New Timit Benchmark for Context-Independent Phone Recognition Using Turbo Fusion.

Timo Lohrenz, Wei Li, Tim Fingscheidt

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

DNN/CNN Acoustic Model Turbo Fusion for Phoneme Recognition.

Timo Lohrenz, Wei Li, Tim Fingscheidt

Proceedings of the 13th ITG Symposium on Speech Communication, 2018

2017

Turbo fusion of magnitude and phase information for DNN-based phoneme recognition.

Timo Lohrenz, Tim Fingscheidt

Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, 2017

2016

Introducing Block-Wise Processing into Turbo Viterbi ASR.

Simon Receveur, Timo Lohrenz, Tim Fingscheidt

Proceedings of the 12th ITG Symposium on Speech Communication, 2016

EXIT Charts for Turbo Automatic Speech Recognition: A Case Study.

Timo Lohrenz, Simon Receveur, Tim Fingscheidt

Proceedings of the 12th ITG Symposium on Speech Communication, 2016