Picture for Lukas Drude

Lukas Drude

Promptformer: Prompted Conformer Transducer for ASR

Add code
Jan 14, 2024
Viaarxiv icon

Multi-View Frequency-Attention Alternative to CNN Frontends for Automatic Speech Recognition

Add code
Jun 12, 2023
Viaarxiv icon

Contextual-Utterance Training for Automatic Speech Recognition

Add code
Oct 27, 2022
Viaarxiv icon

Multi-channel Opus compression for far-field automatic speech recognition with a fixed bitrate budget

Add code
Jun 15, 2021
Figure 1 for Multi-channel Opus compression for far-field automatic speech recognition with a fixed bitrate budget
Figure 2 for Multi-channel Opus compression for far-field automatic speech recognition with a fixed bitrate budget
Figure 3 for Multi-channel Opus compression for far-field automatic speech recognition with a fixed bitrate budget
Figure 4 for Multi-channel Opus compression for far-field automatic speech recognition with a fixed bitrate budget
Viaarxiv icon

Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR

Add code
Jun 04, 2020
Figure 1 for Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR
Figure 2 for Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR
Figure 3 for Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR
Figure 4 for Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR
Viaarxiv icon

End-to-end training of time domain audio separation and recognition

Add code
Dec 25, 2019
Figure 1 for End-to-end training of time domain audio separation and recognition
Figure 2 for End-to-end training of time domain audio separation and recognition
Figure 3 for End-to-end training of time domain audio separation and recognition
Figure 4 for End-to-end training of time domain audio separation and recognition
Viaarxiv icon

Demystifying TasNet: A Dissecting Approach

Add code
Nov 20, 2019
Figure 1 for Demystifying TasNet: A Dissecting Approach
Figure 2 for Demystifying TasNet: A Dissecting Approach
Figure 3 for Demystifying TasNet: A Dissecting Approach
Figure 4 for Demystifying TasNet: A Dissecting Approach
Viaarxiv icon

SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition

Add code
Oct 30, 2019
Figure 1 for SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition
Figure 2 for SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition
Figure 3 for SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition
Figure 4 for SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition
Viaarxiv icon

Unsupervised training of neural mask-based beamforming

Add code
Apr 08, 2019
Figure 1 for Unsupervised training of neural mask-based beamforming
Figure 2 for Unsupervised training of neural mask-based beamforming
Figure 3 for Unsupervised training of neural mask-based beamforming
Figure 4 for Unsupervised training of neural mask-based beamforming
Viaarxiv icon

Unsupervised training of a deep clustering model for multichannel blind source separation

Add code
Apr 02, 2019
Figure 1 for Unsupervised training of a deep clustering model for multichannel blind source separation
Figure 2 for Unsupervised training of a deep clustering model for multichannel blind source separation
Figure 3 for Unsupervised training of a deep clustering model for multichannel blind source separation
Viaarxiv icon