Papers › AutoSpeech: Neural Architecture Search for Speaker Recognition

AutoSpeech: Neural Architecture Search for Speaker Recognition

7 May 2020arXiv:2005.03215archive 2025-07-28

Shaojin Ding, Tianlong Chen, Xinyu Gong, Weiwei Zha, Zhangyang Wang

Speaker recognition systems based on Convolutional Neural Networks (CNNs) are often built with off-the-shelf backbones such as VGG-Net or ResNet. However, these backbones were originally proposed for image classification, and therefore may not be naturally fit for speaker recognition. Due to the prohibitive complexity of manually exploring the design space, we propose the first neural architecture search approach approach for the speaker recognition tasks, named as AutoSpeech. Our algorithm first identifies the optimal operation combination in a neural cell and then derives a CNN model by stacking the neural cell for multiple times. The final speaker recognition model can be obtained by training the derived CNN model through the standard scheme. To evaluate the proposed approach, we conduct experiments on both speaker identification and speaker verification tasks using the VoxCeleb1 dataset. Results demonstrate that the derived CNN architectures from the proposed approach significantly outperform current speaker recognition systems based on VGG-M, ResNet-18, and ResNet-34 back-bones, while enjoying lower model complexity.

PaperPDFCode

Code

TAMU-VITA/AutoSpeech officialmentioned in papermentioned on GitHubpytorch report
JeongwookUm/TEST_AutoSpeech-master mentioned on GitHubpytorch report
VITA-Group/AutoSpeech mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationNeural Architecture SearchSpeaker IdentificationSpeaker RecognitionSpeaker Verificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speaker Identification VoxCeleb1 AutoSpeech (N=8,C=128) Accuracy 87.66 #8 of 12 Archive leaderboard report
Speaker Identification VoxCeleb1 AutoSpeech (N=8,C=128) Number of Params 18M #8 of 12 Archive leaderboard report
Speaker Identification VoxCeleb1 AutoSpeech (N=8,C=128) Top-1 (%) 87.66 #8 of 12 Archive leaderboard report
Speaker Identification VoxCeleb1 AutoSpeech (N=8,C=128) Top-5 (%) 96.01 #8 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections