Related papers: Self-Remixing: Unsupervised Speech Separation via …

Deep learning based models have significantly improved the performance of speech separation with input mixtures like the cocktail party. Prominent methods (e.g., frequency-domain and time-domain speech separation) usually build regression…

We propose a self-supervised learning method using multiple sampling strategies to obtain general-purpose audio representation. Multiple sampling strategies are used in the proposed method to construct contrastive losses from different…

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…

Many of the recent advances in speech separation are primarily aimed at synthetic mixtures of short audio utterances with high degrees of overlap. Most of these approaches need an additional stitching step to stitch the separated speech…

Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require separate training, operate on misaligned objectives, and exhibit…

Semi-supervised learning (SSL) has demonstrated high performance in image classification tasks by effectively utilizing both labeled and unlabeled data. However, existing SSL methods often suffer from poor calibration, with models yielding…

Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years witness great successes in applying self-supervised learning in…

The Sparsespeech model is an unsupervised acoustic model that can generate discrete pseudo-labels for untranscribed speech. We extend the Sparsespeech model to allow for sampling over a random discrete variable, yielding…

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…

The performance of hyperspectral unmixing may be constrained by low spatial resolution, which can be enhanced using super-resolution in a multitask learning way. However, integrating super-resolution and unmixing directly may suffer two…

Dominant researches adopt supervised training for speaker extraction, while the scarcity of ideally clean corpus and channel mismatch problem are rarely considered. To this end, we propose speaker-aware mixture of mixtures training (SAMoM),…

Speech separation aims to separate multiple speech sources from a speech mixture. Although speech separation is well-solved on some existing English speech separation benchmarks, it is worthy of more investigation on the generalizability of…

A mixed sample data augmentation strategy is proposed to enhance the performance of models on audio scene classification, sound event classification, and speech enhancement tasks. While there have been several augmentation methods shown to…

This work presents self-supervised learning methods for developing monaural speaker-specific (i.e., personalized) speech enhancement models. While generalist models must broadly address many speakers, specialist models can adapt their…

Self-supervised pre-trained speech models were shown effective for various downstream speech processing tasks. Since they are mainly pre-trained to map input speech to pseudo-labels, the resulting representations are only effective for the…

Recent semi-supervised learning (SSL) methods are commonly based on pseudo labeling. Since the SSL performance is greatly influenced by the quality of pseudo labels, mutual learning has been proposed to effectively suppress the noises in…

This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is…

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

Separating the individual elements in a musical mixture is an essential process for music analysis and practice. While this is generally addressed using neural networks optimized to mask or transform the time-frequency representation of a…

Self-supervised learning (SSL) offers a powerful way to learn robust, generalizable representations without labeled data. In music, where labeled data is scarce, existing SSL methods typically use generated supervision and multi-view…