paper-with-me

Papers

Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds

2024-09-27 · Hanbin Bae, Pavel Andreev, Azat Saginbaev, Nicholas Babaev, Won-Jun Lee, Hosang Sung, Hoon-Young Cho

This paper introduces a speech enhancement solution tailored for true wireless stereo (TWS) earbuds on-device usage. The solution was specifically designed to support conversations in noisy environments, with active noise cancellation (ANC) activated. The primary challenges for speech enhancement models in this context arise from computational complexity that limits on-device usage and latency that must be less than 3 ms to preserve a live conversation. To address these issues, we evaluated several crucial design elements, including the network architecture and domain, design of loss functions, pruning method, and hardware-specific optimization. Consequently, we demonstrated substantial improvements in speech enhancement quality compared with that in baseline models, while simultaneously reducing the computational complexity and algorithmic latency.

📄 PDF Abstract BibTeX arXiv:2409.18705

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Enhancement

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

RT-LA-VocE: Real-Time Low-SNR Audio-Visual Speech Enhancement

2024-07-10 · Honglie Chen, Rodrigo Mira, Stavros Petridis, Maja Pantic

In this paper, we aim to generate clean speech frame by frame from a live video stream and a noisy audio stream without relying on future inputs. To this end, we propose RT-LA-VocE, which completely re-designs every comp…

Speech Enhancement

Deep low-latency joint speech transmission and enhancement over a gaussian channel

2024-04-30 · Mohammad Bokaei, Jesper Jensen, Simon Doclo, Jan Østergaard

Ensuring intelligible speech communication for hearing assistive devices in low-latency scenarios presents significant challenges in terms of speech enhancement, coding and transmission. In this paper, we propose novel s…

DecoderSpeech Enhancement

Low-latency Monaural Speech Enhancement with Deep Filter-bank Equalizer

2022-02-14 · Chengshi Zheng, Wenzhe Liu, Andong Li, Yuxuan Ke 외

It is highly desirable that speech enhancement algorithms can achieve good performance while keeping low latency for many applications, such as digital hearing aids, acoustically transparent hearing devices, and public a…

Deep LearningSpeech Enhancement

Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latency

2025-06-03 · Bunlong Lay, Rostilav Makarov, Timo Gerkmann

Diffusion models are a class of generative models that have been recently used for speech enhancement with remarkable success but are computationally expensive at inference time. Therefore, these models are impractical f…

GPUSpeech Enhancement

Towards Robust Real-time Audio-Visual Speech Enhancement

2021-12-16 · Mandar Gogate, Kia Dashtipour, Amir Hussain

The human brain contextually exploits heterogeneous sensory information to efficiently perform cognitive tasks including vision and hearing. For example, during the cocktail party situation, the human auditory cortex con…

Speech Enhancement