Enhance Language Identification using Dual-mode Model with Knowledge Distillation

TL;DR

This paper introduces a dual-mode language identification model using knowledge distillation to improve performance on both long and short speech utterances, demonstrating significant relative improvements on the MLS14 dataset.

Contribution

The paper presents a novel dual-mode XSA-LID model with knowledge distillation, effectively enhancing language ID accuracy for varying speech lengths.

Findings

Achieved up to 21.52% relative improvement on 10s speech

Demonstrated effectiveness of dual-mode training with knowledge distillation

Analyzed impact of speech clip variability on LID performance

Abstract

In this paper, we propose to employ a dual-mode framework on the x-vector self-attention (XSA-LID) model with knowledge distillation (KD) to enhance its language identification (LID) performance for both long and short utterances. The dual-mode XSA-LID model is trained by jointly optimizing both the full and short modes with their respective inputs being the full-length speech and its short clip extracted by a specific Boolean mask, and KD is applied to further boost the performance on short utterances. In addition, we investigate the impact of clip-wise linguistic variability and lexical integrity for LID by analyzing the variation of LID performance in terms of the lengths and positions of the mimicked speech clips. We evaluated our approach on the MLS14 data from the NIST 2017 LRE. With the 3~s random-location Boolean mask, our proposed method achieved 19.23%, 21.52% and 8.37% relative improvement in average cost compared with the XSA-LID model on 3s, 10s, and 30s speech, respectively.