Related papers: Unsupervised Speech Segmentation and Variable Rate…

In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose…

The current monaural state of the art tools for speech separation relies on supervised learning. This means that they must deal with permutation problem, they are impacted by the mismatch on the number of speakers used in training and…

Deep learning dominates speech processing but relies on massive datasets, global backpropagation-guided weight updates, and produces entangled representations. Assembly Calculus (AC), which models sparse neuronal assemblies via Hebbian…

Modern supervised semantic segmentation methods are usually finetuned based on the supervised or self-supervised models pre-trained on ImageNet. Recent work shows that transferring the knowledge from CLIP to semantic segmentation via prompt…

It has been generally assumed in the automatic speech recognition (ASR) literature that it is better for models to have access to wider context windows. Yet, many of the potential reasons this might be true in the supervised setting do not…

Cued Speech (CS) is a communication system for deaf people or hearing impaired people, in which a speaker uses it to aid a lipreader in phonetic level by clarifying potentially ambiguous mouth movements with hand shape and positions.…

Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns a discriminative representation by constructing positive and…

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has gained attention for its cost-effectiveness. Most existing methods emphasize inter-class separation, often neglecting the shared semantics among related categories…

Self-supervised learning has become an increasingly important paradigm in the domain of machine intelligence. Furthermore, evidence for self-supervised adaptation, such as contrastive formulations, has emerged in recent computational…

Self-supervised speech representations have been shown to be effective in a variety of speech applications. However, existing representation learning methods generally rely on the autoregressive model and/or observed global dependencies…

Phone level localization of mis-articulation is a key requirement for an automatic articulation error assessment system. A robust phone segmentation technique is essential to aid in real-time assessment of phone level mis-articulations of…

We present a system for the Zero Resource Speech Challenge 2021, which combines a Contrastive Predictive Coding (CPC) with deep cluster. In deep cluster, we first prepare pseudo-labels obtained by clustering the outputs of a CPC network…

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

End-to-end Automatic Speech Recognition (ASR) models are usually trained to optimize the loss of the whole token sequence, while neglecting explicit phonemic-granularity supervision. This could result in recognition errors due to…

Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio…

Semi-supervised learning has demonstrated great potential in medical image segmentation by utilizing knowledge from unlabeled data. However, most existing approaches do not explicitly capture high-level semantic relations between distant…

Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for…

Recent advances in self-supervised contrastive learning yield good image-level representation, which favors classification tasks but usually neglects pixel-level detailed information, leading to unsatisfactory transfer performance to dense…

Convolutional Sparse Coding (CSC) is a well-established image representation model especially suited for image restoration tasks. In this work, we extend the applicability of this model by proposing a supervised approach to convolutional…

Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective for word…