~ similar to 2606.25621· 17 results
This paper introduces own-voice cancellation (OVC) to remove a target speaker from a noisy multi-speaker mixture with low latency.
Hyunjin Choi, Zinu Kim, Junwon Moon, Jeongyun Chae +2 more
The paper proposes StreamSE, a streaming generative speech enhancement model that operates in the latent space of a frozen pretrained neural audio codec.
This paper characterizes the gap between current DNN-based speech enhancement systems and hearing aid constraints, and proposes a lightweight architecture to meet these constraints.
Jiadong Zhao, Dahan Wang, Yu Sun, Leyan Yang +4 more
This paper proposes a method called HALO to reduce the internal frame rate of STFT-based speech enhancement without altering the STFT procedure.
The paper proposes an end-to-end framework called SE-AGCNet that jointly optimizes speech enhancement and automatic gain control for meeting scenarios with significant volume variations.
This paper proposes a skip-free encoder-decoder backbone for flow-matching speech enhancement using Latent Representation Alignment.
A new framework called Geo-DConv is proposed to make multi-channel speech enhancement systems adaptable to diverse microphone array geometries by leveraging microphone coordinates.
Haocheng Dong, Yuheng Lu, Cheng Gong, Shansong Liu +2 more
The paper introduces AudioWeave, a unified model for text-to-audio and audio editing tasks.
This paper proposes a data-driven method for automatic blind audio equalization using a deep neural network and semantic embeddings.
This paper conditions a diffusion-based speech enhancement model on wav2vec 2.0 features using Feature-wise Linear Modulation (FiLM), achieving competitive performance on VoiceBank-DEMAND and LibriMix…
The Autonomous Rectified Flow framework is proposed to improve generative speech enhancement by eliminating explicit time-step conditioning and inferring denoising directions from spatial relationship…