Search results for #WASPAA2023
I have uploaded the video of my #WASPAA2023 on "Fitting Auditory Filterbanks with MuReNN" where MuReNN = Multiresolution Neural Network youtube.com/watch?v=JDHhvb…
I have uploaded the video of my #WASPAA2023 on "Fitting Auditory Filterbanks with MuReNN" where MuReNN = Multiresolution Neural Network youtube.com/watch?v=JDHhvb…
Presented MuReNN at #WASPAA2023 today Thanks to everyone who attended and offered feedback! 📸 @MoummadIlyass
Presented MuReNN at #WASPAA2023 today Thanks to everyone who attended and offered feedback! 📸 @MoummadIlyass https://t.co/1TEG9864Kl
James King presenting our #waspaa2023 paper with @Arshdee71825259 on Compressing Audio CNNs with Graph Centrality Based Filter Pruning / #waspaa @IEEE_WASPAA
Arshdeep Singh (@Arshdee71825259) & Gabriel Bibbo presenting our demo at #waspaa2023 / #waspaa @IEEE_WASPAA
Our team has two presentations at #WASPAA2023 next week 🇺🇸 - Perceptual quality enhancement of sound field synthesis - Sound field estimation in region including scattering objects ap.nii.ac.jp/news/announcem…
Looking forward for WASPAA2023 next week! Here's the video for our paper: #WASPAA2023 youtube.com/watch?v=9JjZ1e… arxiv.org/abs/2305.01864
Great work from Herman that will be presented at #WASPAA2023 in less than two weeks, resulting from an internship with our team @Dolby. Text-to-audio without labels thanks to video data and CLIP.
Great work from Herman that will be presented at #WASPAA2023 in less than two weeks, resulting from an internship with our team @Dolby. Text-to-audio without labels thanks to video data and CLIP.
Happy to share that I'll be presenting our work on text-to-audio synthesis at #WASPAA2023 in New Paltz! 🥳 In this paper, we explore text-audio data free training for text-to-audio synthesis by leveraging the visual modality as a bridge! 🧐 @IEEE_WASPAA youtu.be/YuIJlCi4pNE
Perceptual musical similarity metric learning with graph neural networks hal.science/hal-04178191/ approximating human judgments of timbral similarity with GNNs for sound sample retrieval #WASPAA2023
Our proposal "Improved portable multiple sound spot synthesis system with a baffled circular array of 16 loudspeakers," accepted for #WASPAA2023 Demonstrations. See you in Mohonk!
Preprint for 'Fitting Auditory Filterbanks with Multiresolution Neural Networks' #WASPAA2023 hal.science/hal-04170940 joint work with PhD student Han Han (@LaboLS2N), visiting student Daniel Haider (@ari_oeaw), and colleagues Mathieu Lagrange, Peter Balazs, Martin Haider
"Fitting Auditory Filterbanks with MuReNN" is accepted at #WASPAA2023! where MuReNN = Multiresolution Neural Network Our problem: to design a learning representation for the raw waveform that is - better regularized than Conv1D - more flexible than Gabor1D (as in LEAF)
Another #WASPAA2023 preprint is also available on arXiv. We formulate mel-spectrogram inversion as a single optimization problem by extending GLA and improve the performance from the cascaded approach used in Librosa. Demo: yoshikimas.github.io/signal-reconst… Paper: arxiv.org/abs/2307.12232
Our end-to-end integration of TF-domain speech separation and WavLM-based ASR has been accepted to #WASPAA2023!! End-to-end fine-tuning boosts the ASR performance while decreasing SDR due to artifacts. Demo: yoshikimas.github.io/mimo-iris/ Paper: arxiv.org/abs/2307.12231
📢 Our upcoming #WASPAA2023 paper showcases how we apply the same principle to incorporate the effects of informational masking, enhancing our artificial listeners' performance in estimating the quality of parametric codecs in music signals.
Exciting news! Our paper on “ Predicting thresholds in an auditory overshoot paradigm using a computational subcortical model with efferent feedback” has been accepted into WASPAA! Looking forward to presenting this research in October at New Paltz, NY. #WASPAA2023
WASPAA 2023 is calling for papers! Kudos to the TPC chairs, Juan Pablo Bello and Mounya Elhilali, and general co-chairs, Minje Kim and @NicholasJBryan! #waspaa2023 More information: waspaa.com/call-for-papers
