Related papers: Nonlinear ISA with Auxiliary Variables for Learnin…

Feature extraction plays an important role as a front-end processing block in speaker identification (SI) process. Most of the SI systems utilize like Mel-Frequency Cepstral Coefficients (MFCC), Perceptual Linear Prediction (PLP), Linear…

Speaker-attributed automatic speech recognition (SA-ASR) aims to transcribe speech while assigning transcripts to the corresponding speakers accurately. Existing methods often rely on complex modular systems or require extensive fine-tuning…

Speech intelligibility evaluation for hearing-impaired (HI) listeners is essential for assessing hearing aid performance, traditionally relying on listening tests or intrusive methods like HASPI. However, these methods require clean…

This paper focuses on single-channel semi-supervised speech enhancement. We learn a speaker-independent deep generative speech model using the framework of variational autoencoders. The noise model remains unsupervised because we do not…

In-context learning (ICL) enables large language models (LLMs) to acquire new behaviors from the input sequence alone without any parameter updates. Recent studies have shown that ICL can surpass the original meaning learned in pretraining…

This paper proposes a new architecture for speaker adaptation of multi-speaker neural-network speech synthesis systems, in which an unseen speaker's voice can be built using a relatively small amount of speech data without transcriptions.…

Speaker independent continuous speech separation (SI-CSS) is a task of converting a continuous audio stream, which may contain overlapping voices of unknown speakers, into a fixed number of continuous signals each of which contains no…

Recently, several algorithms have been proposed for independent subspace analysis where hidden variables are i.i.d. processes. We show that these methods can be extended to certain AR, MA, ARMA and ARIMA tasks. Central to our paper is that…

The intuitive interaction between the audio and visual modalities is valuable for cross-modal self-supervised learning. This concept has been demonstrated for generic audiovisual tasks like video action recognition and acoustic scene…

We have developed a sparse mathematical representation of speech that minimizes the number of active model neurons needed to represent typical speech sounds. The model learns several well-known acoustic features of speech such as harmonic…

Unified representation learning for multi-source data integration faces two important challenges: blockwise missingness and blockwise signal heterogeneity. The former arises from sources observing different, yet potentially overlapping,…

Latent image representations arising from vision-language models have proved immensely useful for a variety of downstream tasks. However, their utility is limited by their entanglement with respect to different visual attributes. For…

Previous work has shown that it is possible to improve speech recognition by learning acoustic features from paired acoustic-articulatory data, for example by using canonical correlation analysis (CCA) or its deep extensions. One limitation…

Blind source separation, particularly through independent component analysis (ICA), is widely utilized across various signal processing domains for disentangling underlying components from observed mixed signals, owing to its fully…

To build speech processing methods that can handle speech as naturally as humans, researchers have explored multiple ways of building an invertible mapping from speech to an interpretable space. The articulatory space is a promising…

Self-supervised speech models (S3Ms) have become a common tool for the speech processing community, leveraging representations for downstream tasks. Clustering S3M representations yields discrete speech units (DSUs), which serve as compact…

Independent component analysis (ICA) is an unsupervised learning method popular in functional magnetic resonance imaging (fMRI). Group ICA has been used to search for biomarkers in neurological disorders including autism spectrum disorder…

Independent Component Analysis (ICA) is a popular model for blind signal separation. The ICA model assumes that a number of independent source signals are linearly mixed to form the observed signals. We propose a new algorithm, PEGI (for…

Independent component analysis (ICA) is a cornerstone of modern data analysis. Its goal is to recover a latent random vector S with independent components from samples of X=AS where A is an unknown mixing matrix. Critically, all existing…

The goal of this work is to train discriminative cross-modal embeddings without access to manually annotated data. Recent advances in self-supervised learning have shown that effective representations can be learnt from natural cross-modal…