Picture for Christian Rollwage

Christian Rollwage

Fraunhofer Institute for Digital Media Technology, Project group Hearing, Speech and Audio Technology, Oldenburg, Germany

Speech-dependent Data Augmentation for Own Voice Reconstruction with Hearable Microphones in Noisy Environments

Add code
May 19, 2024
Figure 1 for Speech-dependent Data Augmentation for Own Voice Reconstruction with Hearable Microphones in Noisy Environments
Figure 2 for Speech-dependent Data Augmentation for Own Voice Reconstruction with Hearable Microphones in Noisy Environments
Figure 3 for Speech-dependent Data Augmentation for Own Voice Reconstruction with Hearable Microphones in Noisy Environments
Figure 4 for Speech-dependent Data Augmentation for Own Voice Reconstruction with Hearable Microphones in Noisy Environments
Viaarxiv icon

Multi-Microphone Noise Data Augmentation for DNN-based Own Voice Reconstruction for Hearables in Noisy Environments

Add code
Dec 14, 2023
Viaarxiv icon

Modeling of Speech-dependent Own Voice Transfer Characteristics for Hearables with In-ear Microphones

Add code
Oct 10, 2023
Figure 1 for Modeling of Speech-dependent Own Voice Transfer Characteristics for Hearables with In-ear Microphones
Figure 2 for Modeling of Speech-dependent Own Voice Transfer Characteristics for Hearables with In-ear Microphones
Figure 3 for Modeling of Speech-dependent Own Voice Transfer Characteristics for Hearables with In-ear Microphones
Figure 4 for Modeling of Speech-dependent Own Voice Transfer Characteristics for Hearables with In-ear Microphones
Viaarxiv icon

Speech-dependent Modeling of Own Voice Transfer Characteristics for In-ear Microphones in Hearables

Add code
Sep 15, 2023
Viaarxiv icon

Multilingual Query-by-Example Keyword Spotting with Metric Learning and Phoneme-to-Embedding Mapping

Add code
Apr 19, 2023
Figure 1 for Multilingual Query-by-Example Keyword Spotting with Metric Learning and Phoneme-to-Embedding Mapping
Figure 2 for Multilingual Query-by-Example Keyword Spotting with Metric Learning and Phoneme-to-Embedding Mapping
Figure 3 for Multilingual Query-by-Example Keyword Spotting with Metric Learning and Phoneme-to-Embedding Mapping
Figure 4 for Multilingual Query-by-Example Keyword Spotting with Metric Learning and Phoneme-to-Embedding Mapping
Viaarxiv icon

Speaker-conditioning Single-channel Target Speaker Extraction using Conformer-based Architectures

Add code
May 27, 2022
Figure 1 for Speaker-conditioning Single-channel Target Speaker Extraction using Conformer-based Architectures
Figure 2 for Speaker-conditioning Single-channel Target Speaker Extraction using Conformer-based Architectures
Figure 3 for Speaker-conditioning Single-channel Target Speaker Extraction using Conformer-based Architectures
Figure 4 for Speaker-conditioning Single-channel Target Speaker Extraction using Conformer-based Architectures
Viaarxiv icon

Training Strategies for Own Voice Reconstruction in Hearing Protection Devices using an In-ear Microphone

Add code
May 12, 2022
Figure 1 for Training Strategies for Own Voice Reconstruction in Hearing Protection Devices using an In-ear Microphone
Figure 2 for Training Strategies for Own Voice Reconstruction in Hearing Protection Devices using an In-ear Microphone
Figure 3 for Training Strategies for Own Voice Reconstruction in Hearing Protection Devices using an In-ear Microphone
Viaarxiv icon

Speaker-conditioned Target Speaker Extraction based on Customized LSTM Cells

Add code
Apr 09, 2021
Figure 1 for Speaker-conditioned Target Speaker Extraction based on Customized LSTM Cells
Figure 2 for Speaker-conditioned Target Speaker Extraction based on Customized LSTM Cells
Figure 3 for Speaker-conditioned Target Speaker Extraction based on Customized LSTM Cells
Figure 4 for Speaker-conditioned Target Speaker Extraction based on Customized LSTM Cells
Viaarxiv icon