Related papers: Speech Enhancement using Separable Polling Attenti…
Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement.…
This paper presents our latest investigations on improving automatic speech recognition for noisy speech via speech enhancement. We propose a novel method named Multi-discriminators CycleGAN to reduce noise of input speech and therefore…
Generative models have excelled in audio tasks using approaches such as language models, diffusion, and flow matching. However, existing generative approaches for speech enhancement (SE) face notable challenges: language model-based methods…
Speech enhancement (SE) aims to improve the clarity, intelligibility, and quality of speech signals for various speech enabled applications. However, air-conducted (AC) speech is highly susceptible to ambient noise, particularly in low…
Recent speech enhancement (SE) models increasingly leverage self-supervised learning (SSL) representations for their rich semantic information. Typically, intermediate features are aggregated into a single representation via a lightweight…
We propose UNIVERSE++, a universal speech enhancement method based on score-based diffusion and adversarial training. Specifically, we improve the existing UNIVERSE model that decouples clean speech feature extraction and diffusion. Our…
In recent years, the joint training of speech enhancement front-end and automatic speech recognition (ASR) back-end has been widely used to improve the robustness of ASR systems. Traditional joint training methods only use enhanced speech…
This paper addresses unsupervised diffusion-based single-channel speech enhancement (SE). Prior work in this direction combines a score-based diffusion model trained on clean speech with a Gaussian noise model whose covariance is structured…
Deep learning-based speech enhancement (SE) models have achieved impressive performance in the past decade. Numerous advanced architectures have been designed to deliver state-of-the-art performance; however, their scalability potential…
Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training. This setting prohibits the use of real-world degraded speech data that may better represent the…
This paper presents an efficient speech enhancement (SE) approach that reuses a processing block repeatedly instead of conventional stacking. Rather than increasing the number of blocks for learning deep latent representations, repeating a…
Non-intrusive speech quality assessment (SQA) systems suffer from limited training data and costly human annotations, hindering their generalization to real-time conferencing calls. In this work, we propose leveraging large language models…
Keyword spotting (KWS) on mobile devices generally requires a small memory footprint. However, most current models still maintain a large number of parameters in order to ensure good performance. In this paper, we propose a temporally…
Multi-stage learning is an effective technique to invoke multiple deep-learning modules sequentially. This paper applies multi-stage learning to speech enhancement by using a multi-stage structure, where each stage comprises a…
This paper describes a real-time General Speech Reconstruction (Gesper) system submitted to the ICASSP 2023 Speech Signal Improvement (SSI) Challenge. This novel proposed system is a two-stage architecture, in which the speech restoration…
While speech-based depression detection methods that use speaker-identity features, such as speaker embeddings, are popular, they often compromise patient privacy. To address this issue, we propose a speaker disentanglement method that…
With the advent of deep learning, research on noise-robust automatic speech recognition (ASR) has progressed rapidly. However, ASR performance in noisy conditions of single-channel systems remains unsatisfactory. Indeed, most single-channel…
We propose an approach to extract speaker embeddings that are robust to speaking style variations in text-independent speaker verification. Typically, speaker embedding extraction includes training a DNN for speaker classification and using…
The past decade has witnessed substantial growth of data-driven speech enhancement (SE) techniques thanks to deep learning. While existing approaches have shown impressive performance in some common datasets, most of them are designed only…
This paper focuses on single-channel semi-supervised speech enhancement. We learn a speaker-independent deep generative speech model using the framework of variational autoencoders. The noise model remains unsupervised because we do not…