Danilo de Oliveira

18 papers A 4C 1Misc 2Journal 10Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
Are These Even Words? Quantifying the Gibberishness of Generative Speech Models.
CoRR
Danilo de Oliveira, Tal Peer, Jonas Rochdi, Timo Gerkmann
2025 C conf
Enhancing In-the-Wild Speech Emotion Conversion with Resynthesis-based Duration Modeling.
ASRU
Navin Raj Prabhu, Danilo de Oliveira, Nale Lehmann-Willenbrock, Timo Gerkmann
2025 Misc conf
Investigating Training Objectives for Generative Speech Enhancement.
ICASSP
Julius Richter, Danilo de Oliveira, Timo Gerkmann
2025 J jnl
LipDiffuser: Lip-to-Speech Generation with Conditional Diffusion Models.
CoRR
Danilo de Oliveira, Julius Richter, Tal Peer, Timo Gerkmann
2025 A conf
Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech.
INTERSPEECH
Danilo de Oliveira, Julius Richter, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann
2025 J jnl
Normalize Everything: A Preconditioned Magnitude-Preserving Architecture for Diffusion-Based Speech Enhancement.
CoRR
Julius Richter, Danilo de Oliveira, Timo Gerkmann
2024 Misc conf
Distilling Hubert with LSTMs via Decoupled Knowledge Distillation.
ICASSP
Danilo de Oliveira, Timo Gerkmann
2024 J jnl
Investigating Training Objectives for Generative Speech Enhancement.
CoRR
Julius Richter, Danilo de Oliveira, Timo Gerkmann
2024 — conf
LASER: Language-Queried Speech Enhancer.
IWAENC
Danilo de Oliveira, Eric Grinstein, Patrick A. Naylor, Timo Gerkmann
2024 J jnl
Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech.
CoRR
Danilo de Oliveira, Julius Richter, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann
2024 A conf
The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement.
INTERSPEECH
Danilo de Oliveira, Simon Welker, Julius Richter, Timo Gerkmann
2024 J jnl
The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement.
CoRR
Danilo de Oliveira, Simon Welker, Julius Richter, Timo Gerkmann
2023 J jnl
Distilling HuBERT with LSTMs via Decoupled Knowledge Distillation.
CoRR
Danilo de Oliveira, Timo Gerkmann
2023 A conf
Leveraging Semantic Information for Efficient Self-Supervised Emotion Recognition with Audio-Textual Distilled Models.
INTERSPEECH
Danilo de Oliveira, Navin Raj Prabhu, Timo Gerkmann
2023 J jnl
Leveraging Semantic Information for Efficient Self-Supervised Emotion Recognition with Audio-Textual Distilled Models.
CoRR
Danilo de Oliveira, Navin Raj Prabhu, Timo Gerkmann
2023 J jnl
On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings.
CoRR
Danilo de Oliveira, Julius Richter, Jean-Marie Lemercier, Tal Peer, Timo Gerkmann
2022 A conf
Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes.
INTERSPEECH
Danilo de Oliveira, Tal Peer, Timo Gerkmann
2022 J jnl
Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes.
CoRR
Danilo de Oliveira, Tal Peer, Timo Gerkmann