paper-with-me

홈 › Papers

ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention

2023-05-20 · Jia Qi Yip, Tuan Truong, Dianwen Ng, Chong Zhang, Yukun Ma, Trung Hieu Nguyen, Chongjia Ni, Shengkui Zhao, Eng Siong Chng, Bin Ma

In this paper, we propose ACA-Net, a lightweight, global context-aware speaker embedding extractor for Speaker Verification (SV) that improves upon existing work by using Asymmetric Cross Attention (ACA) to replace temporal pooling. ACA is able to distill large, variable-length sequences into small, fixed-sized latents by attending a small query to large key and value matrices. In ACA-Net, we build a Multi-Layer Aggregation (MLA) block using ACA to generate fixed-sized identity vectors from variable-length inputs. Through global attention, ACA-Net acts as an efficient global feature extractor that adapts to temporal variability unlike existing SV models that apply a fixed function for pooling over the temporal dimension which may obscure information about the signal's non-stationary temporal variability. Our experiments on the WSJ0-1talker show ACA-Net outperforms a strong baseline by 5\% relative improvement in EER using only 1/5 of the parameters.

📄 PDF Abstract BibTeX arXiv:2305.12121

Code (1)

yip-jia-qi/aca-net 공식 구현 pytorch

Tasks

Speaker Verification

Similar Papers 제목 키워드 기반

Post-Training Embedding Alignment for Decoupling Enrollment and Runtime Speaker Recognition Models

2024-01-23 · Chenyang Gao, Brecht Desplanques, Chelsea J. -T. Ju, Aman Chadha 외

Automated speaker identification (SID) is a crucial step for the personalization of a wide range of speech-enabled services. Typical SID systems use a symmetric enrollment-verification framework with a single model to de…

Speaker IdentificationSpeaker Recognition

Cross-lingual Text-independent Speaker Verification using Unsupervised Adversarial Discriminative Domain Adaptation

2019-08-05 · Wei Xia, Jing Huang, John H. L. Hansen

Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data. Being able to improve cross-lingual speaker verification system using unlabeled data can great…

Domain AdaptationSpeaker VerificationText-Independent Speaker Verification

Convolution-Based Channel-Frequency Attention for Text-Independent Speaker Verification

2022-10-31 · Jingyu Li, Yusheng Tian, Tan Lee

Deep convolutional neural networks (CNNs) have been applied to extracting speaker embeddings with significant success in speaker verification. Incorporating the attention mechanism has shown to be effective in improving …

Speaker VerificationText-Independent Speaker Verification

Speaker-Utterance Dual Attention for Speaker and Utterance Verification

2020-08-20 · Tianchi Liu, Rohan Kumar Das, Maulik Madhavi, ShengMei Shen 외

In this paper, we study a novel technique that exploits the interaction between speaker traits and linguistic content to improve both speaker verification and utterance verification performance. We implement an idea of s…

Speaker Verification

Audio-Visual Speaker Verification via Joint Cross-Attention

2023-09-28 · R. Gnana Praveen, Jahangir Alam

Speaker verification has been widely explored using speech signals, which has shown significant improvement using deep models. Recently, there has been a surge in exploring faces and voices as they can offer more complem…

Speaker Verification