479 citations · 1.5k across the 53 of their papers we have counts for
64 papers
Gencho: Room Impulse Response Generation from Reverberant Speech and Text via Diffusion Transformers
Jackie Lin, Jiaqi Su, Nishit Anand +3
Blind room impulse response (RIR) estimation is a core task for capturing and transferring acoustic properties; yet existing methods often suffer from limited modeling capability a…
PromptSep: Generative Audio Separation via Multimodal Prompting
Yutong Wen, Ke Chen, Prem Seetharaman +7
Recent breakthroughs in language-queried audio source separation (LASS) have shown that generative models can achieve higher separation audio quality than traditional masking-based…
Combolutional Neural Networks
Cameron Churchwell, Minje Kim, Paris Smaragdis
Selecting appropriate inductive biases is an essential step in the design of machine learning models, especially when working with audio, where even short clips may contain million…
Continuous-Time Signal Decomposition: An Implicit Neural Generalization of PCA and ICA
Shayan K. Azmoodeh, Krishna Subramani, Paris Smaragdis
We generalize the low-rank decomposition problem, such as principal and independent component analysis (PCA, ICA) for continuous-time vector-valued signals and provide a model-agno…
Adaptive Slimming for Scalable and Efficient Speech Enhancement
Riccardo Miccini, Minje Kim, Clément Laroche +2
Speech enhancement (SE) enables robust speech recognition, real-time communication, hearing aids, and other applications where speech quality is crucial. However, deploying such sy…
User-guided Generative Source Separation
Yutong Wen, Minje Kim, Paris Smaragdis
Music source separation (MSS) aims to extract individual instrument sources from their mixture. While most existing methods focus on the widely adopted four-stem separation setup (…
Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders
Dimitrios Bralios, Jonah Casebeer, Paris Smaragdis
Neural audio codecs and autoencoders have emerged as versatile models for audio compression, transmission, feature-extraction, and latent-space generation. However, a key limitatio…
Learning to Upsample and Upmix Audio in the Latent Domain
Dimitrios Bralios, Paris Smaragdis, Jonah Casebeer
Neural audio autoencoders create compact latent representations that preserve perceptually important information, serving as the foundation for both modern audio compression system…
Generative Data Augmentation Challenge: Synthesis of Room Acoustics for Speaker Distance Estimation
Jackie Lin, Georg Götz, Hermes Sampedro Llopis +9
This paper describes the synthesis of the room acoustics challenge as a part of the generative data augmentation workshop at ICASSP 2025. The challenge defines a unique generative…
Diagnosing Neural Convergence with Topological Alignment Spectra
Tiago F. Tavares, Fabio Ayres, Paris Smaragdis
Representational similarity in neural networks is inherently scale-dependent, yet widely used metrics such as Centered Kernel Alignment (CKA) and Procrustes analysis provide only g…
On Class Separability Pitfalls In Audio-Text Contrastive Zero-Shot Learning
Tiago Tavares, Fabio Ayres, Zhepei Wang +1
Recent advances in audio-text cross-modal contrastive learning have shown its potential towards zero-shot learning. One possibility for this is by projecting item embeddings from p…
Rethinking Non-Negative Matrix Factorization with Implicit Neural Representations
Krishna Subramani, Paris Smaragdis, Takuya Higuchi +1
Non-negative Matrix Factorization (NMF) is a powerful technique for analyzing regularly-sampled data, i.e., data that can be stored in a matrix. For audio, this has led to numerous…
Scaling Up Adaptive Filter Optimizers
Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis
We introduce a new online adaptive filtering method called supervised multi-step adaptive filters (SMS-AF). Our method uses neural networks to control or optimize linear multi-dela…
Meta-AF Echo Cancellation for Improved Keyword Spotting
Jonah Casebeer, Junkai Wu, Paris Smaragdis
Adaptive filters (AFs) are vital for enhancing the performance of downstream tasks, such as speech recognition, sound event detection, and keyword spotting. However, traditional AF…
Audio Editing with Non-Rigid Text Prompts
Francesco Paissan, Luca Della Libera, Zhepei Wang +3
In this paper, we explore audio-editing with non-rigid text edits. We show that the proposed editing pipeline is able to create audio edits that remain faithful to the input audio.…
Mechatronic Generation of Datasets for Acoustics Research
Austin Lu, Ethaniel Moore, Arya Nallanthighall +5
We address the challenge of making spatial audio datasets by proposing a shared mechanized recording space that can run custom acoustic experiments: a Mechatronic Acoustic Research…
Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity
Krishna Subramani, Jean-Marc Valin, Jan Buethe +2
Pitch estimation is an essential step of many speech processing algorithms, including speech coding, synthesis, and enhancement. Recently, pitch estimators based on deep neural net…
Complete and separate: Conditional separation with missing target source attribute completion
Dimitrios Bralios, Efthymios Tzinis, Paris Smaragdis
Recent approaches in source separation leverage semantic information about their input mixtures and constituent sources that when used in conditional separation models can achieve…
Unsupervised Improvement of Audio-Text Cross-Modal Representations
Zhepei Wang, Cem Subakan, Krishna Subramani +4
Recent advances in using language models to obtain cross-modal audio-text representations have overcome the limitations of conventional training approaches that use predefined labe…
A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement
Zhepei Wang, Ritwik Giri, Devansh Shah +3
In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by i…
Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity
Ahmed Mustafa, Jean-Marc Valin, Jan Büthe +2
GAN vocoders are currently one of the state-of-the-art methods for building high-quality neural waveform generative models. However, most of their architectures require dozens of b…
Optimal Condition Training for Target Source Separation
Efthymios Tzinis, Gordon Wichern, Paris Smaragdis +1
Recent research has shown remarkable performance in leveraging multiple extraneous conditional and non-mutually exclusive semantic concepts for sound source separation, allowing th…
Latent Iterative Refinement for Modular Source Separation
Dimitrios Bralios, Efthymios Tzinis, Gordon Wichern +2
Traditional source separation approaches train deep neural network models end-to-end with all the data available at once by minimizing the empirical risk on the whole training set.…
Meta-Learning for Adaptive Filters with Higher-Order Frequency Dependencies
Junkai Wu, Jonah Casebeer, Nicholas J. Bryan +1
Adaptive filters are applicable to many signal processing tasks including acoustic echo cancellation, beamforming, and more. Adaptive filters are typically controlled using algorit…