Faculty

Institution

Unit

Venue

Paris Smaragdis

Professor

UIUC

Affiliations

The Grainger College of Engineering

Department of Electrical and Computer Engineering

Electrical & Computer Engineering

Siebel School of Computing and Data Science

Paris Smaragdis is currently serving as an Electrical And Computer Engineering Professor at Uiuc.

Honors

Create free account to unlock more features

Experiences

Create free account to unlock more features

Education

Create free account to unlock more features

Paris Smaragdis

UIUC

Professor

You can click a keyword to filter the displayed items

speech processing signal processing data science computer science machine learning sound spoken language technology source separation digital signal processing music information retrieval music audio analysis speech recognition speech separation machine learning research neural network (machine learning) signal separation computer music audio signal processing deep learning music science applied mathematics speech communication audio retrieval acoustic signal processing information fusion speech enhancement acoustic modeling multimedia modeling matrix factorization multimedia information processing computational statistics music perception multimedia systems musical expression computational intelligence multi-channel processing auditory modeling multi-speaker speech recognition audio mining speaker localization music classification bayesian analysis localization low-rank approximation sparse representations speech output model compression speech signal sparse neural network robust speech recognition noise reduction distant speech recognition speech synthesis neural network autoencoders adaptive algorithms hidden markov models sound mixtures non-negative matrix factorization convolutional neural networks privacy protection topic models generative adversarial networks array processing nonnegative matrix factorization microphone array polyphonic music transcription blind separation monaural source separation basis functions singing-voice separation bitwise neural networks speech denoising temporal dependencies non-negative approach music technology (electronic and digital)

Notable Scholarly Works

Notable Federal Grants

Collaborators

On Class Separability Pitfalls in Audio-Text Contrastive Zero-Shot Learning. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2025)

Tiago Fernandes TavaresFabio José AyresZhepei WangParis Smaragdis

multimodal learningspoken language technologymultimedia modelingdeep learningmultimedia information processingspeech processingmachine learning researchzero-shot learninglanguagespeech recognitionnatural language processingmachine learningclass separability pitfalls

Audio Editing With Non-Rigid Text Prompts. Interspeech 2022 (2024)

Francesco PaissanLuca Della LiberaZhepei WangParis SmaragdisMirco RavanelliCem Subakan

computer sciencespoken language technologymultimedia modelingstyle transferlatent diffusion modelmultimedia information processinglanguage modelsmusic generationaudio editingdata sciencemusicnon-rigid text promptsnatural language processingcomputer musicmachine learning

Measuring Similarity Between Embedding Spaces Using Induced Neighborhood Graphs. arXiv (Cornell University) (2024)

Tavares, Tiago F.Ayres, FabioSmaragdis, Paris

computer sciencedeep learningcentered kernel alignmentknowledge graph embeddingssemantic evaluationfeature learningmachine learning researchzero-shot learningdata scienceinduced neighborhood graphsmachine learningcifar-100 dataset

Meta-Af Echo Cancellation for Improved Keyword Spotting. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2024)

Jonah CasebeerJunkai WuParis Smaragdis

computer sciencemultimedia information processingspeech processingmusic information retrievalclassifier feedbackdata sciencespeech recognitionmeta-af echo cancellationmeta-learning (computer science)robust speech recognitionmachine learningsound event detection

Noise-Robust Dsp-Assisted Neural Pitch Estimation With Very Low Complexity. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2024)

Krishna SubramaniJean-Marc ValinJan BütheParis SmaragdisMike Goodwin

spoken language technologyspeech synthesissignal processingdeep learningspeech processingneural network (machine learning)pitch estimatorsnew estimatorsspeech outputpitch estimation

On Class Separability Pitfalls in Audio-Text Contrastive Zero-Shot Learning. arXiv (Cornell University) (2024)

Tavares, TiagoAyres, FabioWang, ZhepeiSmaragdis, Paris

computer sciencespoken language technologymultimedia modelingmultimodal learningitem embeddingsmultimodal llmmultimedia information processingspeech processingzero-shot learning evaluationfew-shot learningneural network (machine learning)machine learning researchzero-shot learningdata sciencenatural language processingmultimodal signal processingmachine learningclass separability pitfalls

Rethinking Non-Negative Matrix Factorization With Implicit Neural Representations. arXiv (Cornell University) (2024)

Subramani, KrishnaSmaragdis, ParisHiguchi, TakuyaSouden, Mehrez

low-rank approximationcomputer scienceneural computationfixed vectorssignal processingmatrix factorizationspeech processingneural network (machine learning)machine learning researchdigital signal processingapplied mathematicsnon-negative matrix factorizationimplicit neural representations

Scaling Up Adaptive Filter Optimizers. arXiv (Cornell University) (2024)

Casebeer, JonahBryan, Nicholas J.Smaragdis, Paris

computer sciencespoken language technologyspeech enhancementsignal processingadaptive filter optimizerssupervised lossspeech processingadaptive filterneural network (machine learning)data sciencedigital signal processingacoustic echo cancellationmachine learning

Sound Source Separation Using Latent Variational Block-Wise Disentanglement. arXiv (Cornell University) (2024)

Karim HelwaniMasahito TogamiParis SmaragdisMichael M. Goodwin

spoken language technologysignal processingsoundsource separationsignal separationspeech processingmusic sciencespeech separationapplied mathematics

3D-Printed Acoustic Head Simulators That Talk and Move. The Journal of the Acoustical Society of America (2023)

Xinran YueArya NallanthighallManan MittalAustin LuKanad SarkarRyan M. CoreyParis SmaragdisAndrew C. Singer

head simulatorsmany head simulatorssoundphysical prototypingspeech processingcomputer engineeringdesignacoustic head simulatorsacoustical engineeringacoustic musicsound rendering

1
2
3
4
5
30
10 / page

Paris Smaragdis

Professor

UIUC

Affiliations

The Grainger College of Engineering

Department of Electrical and Computer Engineering

Electrical & Computer Engineering

Siebel School of Computing and Data Science

Paris Smaragdis is currently serving as an Electrical And Computer Engineering Professor at Uiuc.

Honors

Create free account to unlock more features

Experiences

Create free account to unlock more features

Education

Create free account to unlock more features

Paris Smaragdis

UIUC

Professor

You can click a keyword to filter the displayed items

Notable Scholarly Works

Notable Federal Grants

Collaborators

On Class Separability Pitfalls in Audio-Text Contrastive Zero-Shot Learning. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2025)

Tiago Fernandes TavaresFabio José AyresZhepei WangParis Smaragdis

Audio Editing With Non-Rigid Text Prompts. Interspeech 2022 (2024)

Francesco PaissanLuca Della LiberaZhepei WangParis SmaragdisMirco RavanelliCem Subakan

Measuring Similarity Between Embedding Spaces Using Induced Neighborhood Graphs. arXiv (Cornell University) (2024)

Tavares, Tiago F.Ayres, FabioSmaragdis, Paris

Meta-Af Echo Cancellation for Improved Keyword Spotting. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2024)

Jonah CasebeerJunkai WuParis Smaragdis

Noise-Robust Dsp-Assisted Neural Pitch Estimation With Very Low Complexity. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2024)

Krishna SubramaniJean-Marc ValinJan BütheParis SmaragdisMike Goodwin

spoken language technologyspeech synthesissignal processingdeep learningspeech processingneural network (machine learning)pitch estimatorsnew estimatorsspeech outputpitch estimation

On Class Separability Pitfalls in Audio-Text Contrastive Zero-Shot Learning. arXiv (Cornell University) (2024)

Tavares, TiagoAyres, FabioWang, ZhepeiSmaragdis, Paris

Rethinking Non-Negative Matrix Factorization With Implicit Neural Representations. arXiv (Cornell University) (2024)

Subramani, KrishnaSmaragdis, ParisHiguchi, TakuyaSouden, Mehrez

Scaling Up Adaptive Filter Optimizers. arXiv (Cornell University) (2024)

Casebeer, JonahBryan, Nicholas J.Smaragdis, Paris

Sound Source Separation Using Latent Variational Block-Wise Disentanglement. arXiv (Cornell University) (2024)

Karim HelwaniMasahito TogamiParis SmaragdisMichael M. Goodwin

spoken language technologysignal processingsoundsource separationsignal separationspeech processingmusic sciencespeech separationapplied mathematics

3D-Printed Acoustic Head Simulators That Talk and Move. The Journal of the Acoustical Society of America (2023)

Xinran YueArya NallanthighallManan MittalAustin LuKanad SarkarRyan M. CoreyParis SmaragdisAndrew C. Singer

head simulatorsmany head simulatorssoundphysical prototypingspeech processingcomputer engineeringdesignacoustic head simulatorsacoustical engineeringacoustic musicsound rendering

1
2
3
4
5
30
10 / page