Staircase Network: Structural Language Identification Via Hierarchical Attentive Units

Abstract

Language recognition system is typically trained directly to optimize classification error on the target language labels, without using the external, or meta-information in the estimation of the model parameters. However labels are not independent of each other, there is a dependency enforced by, for example, the language family, which affects negatively on classification. The other external information sources (e.g. audio encoding, telephony or video speech) can also decrease classification accuracy. In this paper, we attempt to solve these issues by constructing a deep hierarchical neural network, where different levels of meta-information are encapsulated by attentive prediction units and also embedded into the training progress. The proposed method learns auxiliary tasks to obtain robust internal representation and to construct a variant of attentive units within the hierarchical model. The final result is the structural prediction of the target language and a closely related langu

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keytrong2018staircase

Related papers

• A Semisupervised Approach For Language Identification Based On Ladder Networks (2016)0.00
• Weakly Supervised Training Of Hierarchical Attention Networks For Speaker Identification (2020)3.58
• Towards Relevance And Sequence Modeling In Language Recognition (2020)9.23
• Streaming Language Identification Using Combination Of Acoustic Representations And ASR Hypotheses (2020)0.00
• Language Learning Using Speech To Image Retrieval (2019)9.41
• Soft Language Identification For Language-agnostic Many-to-one End-to-end Speech Translation (2024)0.00
• Learning Hierarchical Discrete Linguistic Units From Visually-grounded Speech (2019)0.00
• Multi-language Identification Using Convolutional Recurrent Neural Network (2016)13.88