Related papers: SuPseudo: A Pseudo-supervised Learning Method for …
In recent years, exploring effective sound separation (SSep) techniques to improve overlapping sound event detection (SED) attracts more and more attention. Creating accurate separation signals to avoid the catastrophic error accumulation…
Self-supervised representation learning approaches have grown in popularity due to the ability to train models on large amounts of unlabeled data and have demonstrated success in diverse fields such as natural language processing, computer…
Language Model (LM)-based speech enhancement (SE) has recently emerged as a promising direction, but existing approaches predominantly rely on token-level likelihood objectives that weakly reflect human perception. This mismatch limits…
Deep learning-based speech enhancement has shown unprecedented performance in recent years. The most popular mono speech enhancement frameworks are end-to-end networks mapping the noisy mixture into an estimate of the clean speech. With…
Since the advent of Deep Learning (DL), Speech Enhancement (SE) models have performed well under a variety of noise conditions. However, such systems may still introduce sonic artefacts, sound unnatural, and restrict the ability for a user…
The current dominant approach for neural speech enhancement is based on supervised learning by using simulated training data. The trained models, however, often exhibit limited generalizability to real-recorded data. To address this, this…
Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion. On the…
Integrating front-end speech enhancement (SE) models with self-supervised learning (SSL)-based speech models is effective for downstream tasks in noisy conditions. SE models are commonly fine-tuned using SSL representations with mean…
Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…
We revisit self-training in the context of end-to-end speech recognition. We demonstrate that training with pseudo-labels can substantially improve the accuracy of a baseline model. Key to our approach are a strong baseline acoustic and…
Speech enhancement (SE) aims to extract the clean waveform from noise-contaminated measurements to improve the speech quality and intelligibility. Although learning-based methods can perform much better than traditional counterparts, the…
Personalized speech enhancement (PSE) is a real-time SE approach utilizing a speaker embedding of a target person to remove background noise, reverberation, and interfering voices. To deploy a PSE model for full duplex communications, the…
Recent studies have shown that the benefits provided by self-supervised pre-training and self-training (pseudo-labeling) are complementary. Semi-supervised fine-tuning strategies under the pre-training framework, however, remain…
Recent advancements in Self-Supervised Learning (SSL) have shown promising results in Speaker Verification (SV). However, narrowing the performance gap with supervised systems remains an ongoing challenge. Several studies have observed that…
While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue. In this work, we propose a self-training method with an end-to-end system…
Recent autoregressive transformer-based speech enhancement (SE) methods have shown promising results by leveraging advanced semantic understanding and contextual modeling of speech. However, these approaches often rely on complex…
Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction. In contrast, some recent works explore SE via generative…
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…
The scarcity of speaker-annotated far-field speech presents a significant challenge in developing high-performance far-field speaker verification (SV) systems. While data augmentation using large-scale near-field speech has been a common…
Self-Supervised Learning (SSL) has allowed leveraging large amounts of unlabeled speech data to improve the performance of speech recognition models even with small annotated datasets. Despite this, speech SSL representations may fail while…