Related papers: Improving Semi-supervised End-to-end Automatic Spe…

We present several methods to improve the generalisation of language identification (LID) systems to new speakers and to new domains. These methods involve Spectral augmentation, where spectrograms are masked in the frequency or time bands…

Style transfer usually refers to the task of applying color and texture information from a specific style image to a given content image while preserving the structure of the latter. Here we tackle the more generic problem of semantic style…

Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers. It is well-known that large-margin training can improve the generalisation…

Estimating time-frequency domain masks for single-channel speech enhancement using deep learning methods has recently become a popular research field with promising results. In this paper, we propose a novel components loss (CL) for the…

Recent works on speech spoofing countermeasures still lack generalization ability to unseen spoofing attacks. This is one of the key issues of ASVspoof challenges especially with the rapid development of diverse and high-quality spoofing…

Purpose: The objective of this work is to introduce an advanced framework designed to enhance ultrasound images, especially those captured by portable hand-held devices, which often produce lower quality images due to hardware constraints.…

Integrated sensing and communications (ISAC) is envisioned as one of the key enablers of next-generation wireless systems, offering improved hardware, spectral, and energy efficiencies. In this paper, we consider an ISAC transceiver with an…

While speaker adaptation for end-to-end speech synthesis using speaker embeddings can produce good speaker similarity for speakers seen during training, there remains a gap for zero-shot adaptation to unseen speakers. We investigate…

Training (source) domain bias affects state-of-the-art object detectors, such as Faster R-CNN, when applied to new (target) domains. To alleviate this problem, researchers proposed various domain adaptation methods to improve object…

The goal of unsupervised image-to-image translation is to map images from one domain to another without the ground truth correspondence between the two domains. State-of-art methods learn the correspondence using large numbers of unpaired…

The performance of face photo-sketch translation has improved a lot thanks to deep neural networks. GAN based methods trained on paired images can produce high-quality results under laboratory settings. Such paired datasets are, however,…

Speech enhancement techniques based on deep learning have brought significant improvement on speech quality and intelligibility. Nevertheless, a large gain in speech quality measured by objective metrics, such as perceptual evaluation of…

As end-to-end automatic speech recognition (ASR) models reach promising performance, various downstream tasks rely on good confidence estimators for these systems. Recent research has shown that model-based confidence estimators have a…

This article presents a novel approach for learning domain-invariant speaker embeddings using Generative Adversarial Networks. The main idea is to confuse a domain discriminator so that is can't tell if embeddings are from the source or…

We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvements have been achieved by the community in the recent period, the quality of synthesized images is far from satisfactory due to three…

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…

Recent advances in deep learning show that end-to-end speech to text translation model is a promising approach to direct the speech translation field. In this work, we provide an overview of different end-to-end architectures, as well as…

Despite being trained on massive and diverse datasets, speech self-supervised encoders are generally used for downstream purposes as mere frozen feature extractors or model initializers before fine-tuning. The former severely limits the…

Speech recognition systems often struggle with data domains that have not been included in the training. To address this, unsupervised domain adaptation has been explored with ensemble and multi-stage teacher-student training methods…

Language identification from speech is a common preprocessing step in many spoken language processing systems. In recent years, this field has seen fast progress, mostly due to the use of self-supervised models pretrained on multilingual…