A Semisupervised Approach For Language Identification Based On Ladder Networks

Abstract

In this study we address the problem of training a neuralnetwork for language identification using both labeled and unlabeled speech samples in the form of i-vectors. We propose a neural network architecture that can also handle out-of-set languages. We utilize a modified version of the recently proposed Ladder Network semisupervised training procedure that optimizes the reconstruction costs of a stack of denoising autoencoders. We show that this approach can be successfully applied to the case where the training dataset is composed of both labeled and unlabeled acoustic data. The results show enhanced language identification on the NIST 2015 language identification dataset.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybenreuven2016a

Related papers

• Improving Embedding Extraction For Speaker Verification With Ladder Network (2020)0.00
• Staircase Network: Structural Language Identification Via Hierarchical Attentive Units (2018)2.26
• Joint Unsupervised And Supervised Learning For Context-aware Language Identification (2023)2.26
• Improved Language Identification Through Cross-lingual Self-supervised Learning (2021)10.61
• Spoken Language Identification Using Convnets (2019)9.59
• Phonetic Temporal Neural Model For Language Identification (2017)12.40
• Multi-language Identification Using Convolutional Recurrent Neural Network (2016)13.88
• Towards Relevance And Sequence Modeling In Language Recognition (2020)9.23