Marco Tagliasacchi
10 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (4) π Academic Marathon (5) π Cross-Pollinator (15)
π
Conference Polyglot
(4)
π
Academic Marathon
(5)
π
Cross-Pollinator
(15)
π
Century Club
(10)
π₯
Unstoppable
(6)
ποΈ
Keyword Collector
(55)
Conferences
INTERSPEECH (7)
ICLR (1)
JMLR (1)
NAACL (1)
Top co-authors
Keywords
neural network
(3)
audio generation
(2)
speech synthesis
(2)
multi-modal learning
(2)
transfer learning
(1)
speech separation
(1)
transformer architecture
(1)
speech recognition
(1)
model selection
(1)
prosody analysis
(1)
multimodal learning
(1)
speaker recognition
(1)
automatic speech recognition
(1)
adversarial training
(1)
speech inpainting
(1)
speech enhancement
(1)
embedding learning
(1)
sound source separation
(1)
speech dereverberation
(1)
representation learning
(1)
Papers
MAD Speech: Measures of Acoustic Diversity of Speech
NAACL 2025
Data Summarization via Bilevel Optimization
JMLR 2024
Real time spectrogram inversion on mobile phone
INTERSPEECH 2023
TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition
INTERSPEECH 2023
Text-Driven Separation of Arbitrary Sounds
INTERSPEECH 2022
CycleGAN-based Unpaired Speech Dereverberation
INTERSPEECH 2022
SpeechPainter: Text-conditioned Speech Inpainting
INTERSPEECH 2022
LEAF: A Learnable Frontend for Audio Classification
ICLR 2021
SEANet: A Multi-Modal Speech Enhancement Network
INTERSPEECH 2020
Towards Learning a Universal Non-Semantic Representation of Speech
INTERSPEECH 2020