paper-with-me

Papers

NeXt-TDNN: Modernizing Multi-Scale Temporal Convolution Backbone for Speaker Verification

2023-12-14 · Hyun-Jun Heo, Ui-Hyeop Shin, Ran Lee, YoungJu Cheon, Hyung-Min Park

In speaker verification, ECAPA-TDNN has shown remarkable improvement by utilizing one-dimensional(1D) Res2Net block and squeeze-and-excitation(SE) module, along with multi-layer feature aggregation (MFA). Meanwhile, in vision tasks, ConvNet structures have been modernized by referring to Transformer, resulting in improved performance. In this paper, we present an improved block design for TDNN in speaker verification. Inspired by recent ConvNet structures, we replace the SE-Res2Net block in ECAPA-TDNN with a novel 1D two-step multi-scale ConvNeXt block, which we call TS-ConvNeXt. The TS-ConvNeXt block is constructed using two separated sub-modules: a temporal multi-scale convolution (MSC) and a frame-wise feed-forward network (FFN). This two-step design allows for flexible capturing of inter-frame and intra-frame contexts. Additionally, we introduce global response normalization (GRN) for the FFN modules to enable more selective feature propagation, similar to the SE module in ECAPA-TDNN. Experimental results demonstrate that NeXt-TDNN, with a modernized backbone block, significantly improved performance in speaker verification tasks while reducing parameter size and inference time. We have released our code for future studies.

📄 PDF Abstract BibTeX arXiv:2312.08603

Code (1)

dmlguq456/next_tdnn_asv 공식 구현 pytorch

Tasks

Speaker Verification

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Multi-Head Attention 설명 없음
Attention 설명 없음
Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Batch Normalization 설명 없음
Kaiming Initialization 설명 없음

Similar Papers 제목 키워드 기반

Modernizing Open-Set Speech Language Identification

2022-05-20 · Mustafa Eyceoz, Justin Lee, Homayoon Beigi

While most modern speech Language Identification methods are closed-set, we want to see if they can be modified and adapted for the open-set problem. When switching to the open-set problem, the solution gains the ability…

Language IdentificationSpeech Language Identification

MACCIF-TDNN: Multi aspect aggregation of channel and context interdependence features in TDNN-based speaker verification

2021-07-07 · Fangyuan Wang, Zhigang Song, Hongchen Jiang, Bo Xu

Most of the recent state-of-the-art results for speaker verification are achieved by X-vector and its subsequent variants. In this paper, we propose a new network architecture which aggregates the channel and context int…

Speaker Verification

Deformable TDNN with adaptive receptive fields for speech recognition

2021-04-30 · Keyu An, Yi Zhang, Zhijian Ou

Time Delay Neural Networks (TDNNs) are widely used in both DNN-HMM based hybrid speech recognition systems and recent end-to-end systems. Nevertheless, the receptive fields of TDNNs are limited and fixed, which is not de…

speech-recognitionSpeech Recognition

Improved TDNNs using Deep Kernels and Frequency Dependent Grid-RNNs

2018-02-18 · Florian Kreyssig, Chao Zhang, Philip Woodland

Time delay neural networks (TDNNs) are an effective acoustic model for large vocabulary speech recognition. The strength of the model can be attributed to its ability to effectively model long temporal contexts. However,…

speech-recognitionSpeech Recognition

Infant Cry Emotion Recognition Using Improved ECAPA-TDNN with Multiscale Feature Fusion and Attention Enhancement

2025-06-23 · Junyu Zhou, Yanxiong Li, Haolin Yu

Infant cry emotion recognition is crucial for parenting and medical applications. It faces many challenges, such as subtle emotional variations, noise interference, and limited data. The existing methods lack the ability…

Emotion Recognition