Related papers: Multi-Objective Learning and Mask-Based Post-Proce…

Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent…

Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent…

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…

Meta-learning has recently become a research hotspot in speaker verification (SV). We introduce two methods to improve the meta-learning training for SV in this paper. For the first method, a backbone embedding network is first jointly…

Natural language processing (NLP) tasks tend to suffer from a paucity of suitably annotated training data, hence the recent success of transfer learning across a wide variety of them. The typical recipe involves: (i) training a deep,…

In this paper, we present a method that allows to further improve speech enhancement obtained with recently introduced Deep Neural Network (DNN) models. We propose a multi-channel refinement method of time-frequency masks obtained with…

This paper introduces our approaches for the Mask and Breathing Sub-Challenge in the Interspeech COMPARE Challenge 2020. For the mask detection task, we train deep convolutional neural networks with filter-bank energies, gender-aware…

In this paper we propose a Deep Neural Network (DNN) based Speech Enhancement (SE) system that is designed to maximize an approximation of the Short-Time Objective Intelligibility (STOI) measure. We formalize an approximate-STOI cost…

The quality of speech codecs deteriorates at low bitrates due to high quantization noise. A post-filter is generally employed to enhance the quality of the coded speech. In this paper, a data-driven post-filter relying on masking in the…

We present an efficient method of utilizing pretrained language models, where we learn selective binary masks for pretrained weights in lieu of modifying them through finetuning. Extensive evaluations of masking BERT and RoBERTa on a series…

Transformer-based models attain excellent results and generalize well when trained on sufficient amounts of data. However, constrained by the limited data available in the audio domain, most transformer-based models for audio tasks are…

We show that a Modular Neural Network (MNN) can combine various speech enhancement modules, each of which is a Deep Neural Network (DNN) specialized on a particular enhancement job. Differently from an ordinary ensemble technique that…

Multichannel processing is widely used for speech enhancement but several limitations appear when trying to deploy these solutions to the real-world. Distributed sensor arrays that consider several devices with a few microphones is a viable…

In this paper, we investigate a deep learning approach for speech denoising through an efficient ensemble of specialist neural networks. By splitting up the speech denoising task into non-overlapping subproblems and introducing a…

Adapting language models (LMs) to novel domains is often achieved through fine-tuning a pre-trained LM (PLM) on domain-specific data. Fine-tuning introduces new knowledge into an LM, enabling it to comprehend and efficiently perform a…

Background. Previous state-of-the-art systems on Drug Name Recognition (DNR) and Clinical Concept Extraction (CCE) have focused on a combination of text "feature engineering" and conventional machine learning algorithms such as conditional…

Pre-trained self-supervised learning (SSL) models have achieved remarkable success in various speech tasks. However, their potential in target speech extraction (TSE) has not been fully exploited. TSE aims to extract the speech of a target…

Deep learning has become very popular for tasks such as predictive modeling and pattern recognition in handling big data. Deep learning is a powerful machine learning method that extracts lower level features and feeds them forward for the…

Monaural source separation is important for many real world applications. It is challenging because, with only a single channel of information available, without any constraints, an infinite number of solutions are possible. In this paper,…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…