A Compact End-to-End Model with Local and Global Context for Spoken Language Identification

Jia, Fu; Koluguri, Nithin Rao; Balam, Jagadeesh; Ginsburg, Boris

doi:10.21437/interspeech.2023-2310

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both models have been introduced into language recognition due to their outstanding performance [23][24][25][26]. While CNN-based models are effective in speech processing tasks, their limited kernel size often restricts them to capturing only local context, this is particularly disadvantageous for LID tasks, where the quantity of available context is crucial [27].…”

Section: Introductionmentioning

confidence: 99%

Branch-Transformer: A Parallel Branch Architecture to Capture Local and Global Features for Language Identification

Li,

Liu,

Fang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Currently, an increasing number of people are opting to use transformer models or conformer models for language identification, achieving outstanding results. Among them, transformer models based on self-attention can only capture global information, lacking finer local details. There are also approaches that employ conformer models by concatenating convolutional neural networks and transformers to capture both local and global information. However, this static single-branch architecture is difficult to interpret and modify, and it incurs greater inference difficulty and computational costs compared to dual-branch models. Therefore, in this paper, we propose a novel model called Branch-transformer (B-transformer). In contrast to traditional transformers, it consists of parallel dual-branch structures. One branch utilizes self-attention to capture global information, while the other employs a Convolutional Gated Multi-Layer Perceptron (cgMLP) module to extract local information. We also investigate various fusion methods for integrating global and local information and experimentally validate the effectiveness of our approach on the NIST LRE 2017 dataset.

show abstract