Related papers: Metric-oriented Speech Enhancement using Diffusion…
We propose DiffSep, a new single channel source separation method based on score-matching of a stochastic differential equation (SDE). We craft a tailored continuous time diffusion-mixing process starting from the separated sources and…
It is promising to design a single model that can suppress various distortions and improve speech quality, i.e., universal speech enhancement (USE). Compared to supervised learning-based predictive methods, diffusion-based generative models…
Diffusion models have gained attention in speech enhancement tasks, providing an alternative to conventional discriminative methods. However, research on target speech extraction under multi-speaker noisy conditions remains relatively…
Speech enhancement(SE) aims to recover clean speech from noisy recordings. Although generative approaches such as score matching and Schrodinger bridge have shown strong effectiveness, they are often computationally expensive. Flow matching…
Achieving a balance between lightweight design and high performance remains a challenging task for speech enhancement. In this paper, we introduce Multi-path Enhanced Taylor (MET) Transformer based U-net for Speech Enhancement (MUSE), a…
We propose a multi-task universal speech enhancement (MUSE) model that can perform five speech enhancement (SE) tasks: dereverberation, denoising, speech separation (SS), target speaker extraction (TSE), and speaker counting. This is…
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…
We introduce DiffuseST, a low-latency, direct speech-to-speech translation system capable of preserving the input speaker's voice zero-shot while translating from multiple source languages into English. We experiment with the synthesizer…
Diffusion models have recently achieved impressive results in reconstructing images from noisy inputs, and similar ideas have been applied to speech enhancement by treating time-frequency representations as images. With the ubiquity of…
The Transformer architecture has demonstrated a superior ability compared to recurrent neural networks in many different natural language processing applications. Therefore, our study applies a modified Transformer in a speech enhancement…
The performance of deep neural network-based speech enhancement systems typically increases with the training dataset size. However, studies that investigated the effect of training dataset size on speech enhancement performance did not…
Supervised learning based on a deep neural network recently has achieved substantial improvement on speech enhancement. Denoising networks learn mapping from noisy speech to clean one directly, or to a spectrum mask which is the ratio…
MOS (Mean Opinion Score) is a subjective method used for the evaluation of a system's quality. Telecommunications (for voice and video), and speech synthesis systems (for generated speech) are a few of the many applications of the method.…
Since its inception, the field of deep speech enhancement has been dominated by predictive (discriminative) approaches, such as spectral mapping or masking. Recently, however, novel generative approaches have been applied to speech…
Diffusion-based text-to-speech (TTS) systems have made remarkable progress in zero-shot speech synthesis, yet optimizing all components for perceptual metrics remains challenging. Prior work with DMOSpeech demonstrated direct metric…
This paper introduces a lightweight deep learning model for real-time speech enhancement, designed to operate efficiently on resource-constrained devices. The proposed model leverages a compact architecture that facilitates rapid inference…
To obtain improved speech enhancement models, researchers often focus on increasing performance according to specific instrumental metrics. However, when the same metric is used in a loss function to optimize models, it may be detrimental…
Recently, more and more personalized speech enhancement systems (PSE) with excellent performance have been proposed. However, two critical issues still limit the performance and generalization ability of the model: 1) Acoustic environment…
We present MooseNet, a trainable speech metric that predicts the listeners' Mean Opinion Score (MOS). We propose a novel approach where the Probabilistic Linear Discriminative Analysis (PLDA) generative model is used on top of an embedding…
The objective speech quality assessment is usually conducted by comparing received speech signal with its clean reference, while human beings are capable of evaluating the speech quality without any reference, such as in the mean opinion…