Related papers: Personalized Speech Enhancement through Self-Super…
Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…
Current speaker anonymization methods, especially with self-supervised learning (SSL) models, require massive computational resources when hiding speaker identity. This paper proposes an effective and parameter-efficient speaker…
Faced with the scarcity of clean label data in real scenarios, seismic denoising methods based on supervised learning (SL) often encounter performance limitations. Specifically, when a model trained on synthetic data is directly applied to…
Self-Supervised Learning (SSL) has become a powerful solution to extract rich representations from unlabeled data. Yet, SSL research is mostly focused on clean, curated and high-quality datasets. As a result, applying SSL on noisy data…
Personalised speech enhancement (PSE), which extracts only the speech of a target user and removes everything else from a recorded audio clip, can potentially improve users' experiences of audio AI modules deployed in the wild. To support a…
Personalized speech enhancement (PSE) models achieve promising results compared with unconditional speech enhancement models due to their ability to remove interfering speech in addition to background noise. Unlike unconditional speech…
Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…
We extend the blindspot model for self-supervised denoising to handle Poisson-Gaussian noise and introduce an improved training scheme that avoids hyperparameters and adapts the denoiser to the test data. Self-supervised models for…
Self-supervised learning (SSL) has grown in interest within the speech processing community, since it produces representations that are useful for many downstream tasks. SSL uses global and contextual methods to produce robust…
Speech enhancement for voice pickup in hearables aims to improve the user's voice by suppressing noise and interfering talkers, while maintaining own-voice quality. For single-channel methods, it is particularly challenging to distinguish…
When data is generated by multiple sources, conventional training methods update models assuming equal reliability for each source and do not consider their individual data quality. However, in many applications, sources have varied levels…
Voice assistants are now widely available, and to activate them a keyword spotting (KWS) algorithm is used. Modern KWS systems are mainly trained using supervised learning methods and require a large amount of labelled data to achieve a…
Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using…
Recent audio LLMs have emerged rapidly, demonstrating strong generalization across various speech tasks. However, given the inherent complexity of speech signals, these models inevitably suffer from performance degradation in specific…
Animal vocalization denoising is a task similar to human speech enhancement, which is relatively well-studied. In contrast to the latter, it comprises a higher diversity of sound production mechanisms and recording environments, and this…
Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…
We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest…
We present a self-supervised speech restoration method without paired speech corpora. Because the previous general speech restoration method uses artificial paired data created by applying various distortions to high-quality speech corpora,…
Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues as there exists little parallel S2ST data, compared to the amount of data available for conventional cascaded systems that consist of automatic speech…