相关论文: JEPA as a Neural Tokenizer: Learning Robust Speech…

In this paper, we present ECAPA2, a novel hybrid neural network architecture and training strategy to produce robust speaker embeddings. Most speaker verification models are based on either the 1D- or 2D-convolutional operation, often…

Recent advancements in self-supervised learning in the point cloud domain have demonstrated significant potential. However, these methods often suffer from drawbacks, including lengthy pre-training time, the necessity of reconstruction in…

Visual Speech Recognition (VSR) tasks are generally recognized to have a lower theoretical performance ceiling than Automatic Speech Recognition (ASR), owing to the inherent limitations of conveying semantic information visually. To…

In this study, we aim to explore Multitask Speech Language Model (SpeechLM) efficient inference via token reduction. Unlike other modalities such as vision or text, speech has unique temporal dependencies, making previous efficient…

Joint-Embedding Predictive Architectures (JEPAs) provide a simpleframework for learning world models by predicting future latent representations.However, JEPA training is subject to a bias-variance tradeoff.Without sufficient structural…

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…

Self-supervised audio representation learning offers an attractive alternative for obtaining generic audio embeddings, capable to be employed into various downstream tasks. Published approaches that consider both audio and words/tags…

Semi-supervised learning has emerged as a powerful paradigm for leveraging large amounts of unlabeled data to improve the performance of machine learning models when labeled data are scarce. Among existing approaches, methods derived from…

We propose the first method to adaptively modify the duration of a given speech signal. Our approach uses a Bayesian framework to define a latent attention map that links frames of the input and target utterances. We train a masked…

Auditory attention decoding (AAD) is the process of identifying the attended speech in a multi-talker environment using brain signals, typically recorded through electroencephalography (EEG). Over the past decade, AAD has undergone…

Depression detection research has increased over the last few decades, one major bottleneck of which is the limited data availability and representation learning. Recently, self-supervised learning has seen success in pretraining text…

Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…

In recent advancements in unsupervised visual representation learning, the Joint-Embedding Predictive Architecture (JEPA) has emerged as a significant method for extracting visual features from unlabeled imagery through an innovative…

Learning manipulable representations of the world and its dynamics is central to AI. Joint-Embedding Predictive Architectures (JEPAs) offer a promising blueprint, but lack of practical guidance and theory has led to ad-hoc R&D. We present a…

The end-to-end (E2E) automatic speech recognition (ASR) systems are often required to operate in reverberant conditions, where the long-term sub-band envelopes of the speech are temporally smeared. In this paper, we develop a feature…

In this paper, we propose an ensemble of deep neural networks along with data augmentation (DA) learned using effective speech-based features to recognize emotions from speech. Our ensemble model is built on three deep neural network-based…

World models for partially observed environments must imagine multiple compatible hidden futures and steer between them under counterfactual actions. Joint Embedding Predictive Architectures (JEPAs) do this in latent space, but a…

We analyze the impact of speaker adaptation in end-to-end automatic speech recognition models based on transformers and wav2vec 2.0 under different noise conditions. By including speaker embeddings obtained from x-vector and ECAPA-TDNN…

Current state-of-the-art speech recognition models are trained to map acoustic signals into sub-lexical units. While these models demonstrate superior performance, they remain vulnerable to out-of-distribution conditions such as background…

Neuron segmentation from electron microscopy (EM) volumes is crucial for understanding brain circuits, yet the complex neuronal structures in high-resolution EM images present significant challenges. EM data exhibits unique characteristics…