Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Cross-lingual Embedding Clustering for Hierarchical Softmax in Low-Resource Multilingual Speech Recognition

Domain:

natural language processing

Record type:

paper
Creator:
YanLiuLi,Che
Host:avatar
We present a novel approach centered on the decoding stage of Automatic Speech Recognition (ASR) that enhances multilingual performance, especially for low-resource languages. It utilizes a cross-lingual embedding clustering method to construct a hierarchical Softmax (H-Softmax) decoder, which enables similar tokens across different languages to share similar decoder representations. It addresses the limitations of the previous Huffman-based H-Softmax method, which relied on shallow features in token similarity assessments. Through experiments on a downsampled dataset of 15 languages, we demonstrate the effectiveness of our approach in improving low-resource multilingual ASR accuracy.

Visit

arxiv.org

Tasks

automatic speech recognitionspeech processing

Tags

Computation and LanguageSoundAudio and Speech Processing

Similar

XLST: Cross-lingual Self-training to Learn Multilingual Representation for Low Resource Speech RecognitionExploiting Adapters for Cross-lingual Low-resource Speech RecognitionDonorRank: Donor Language Selection for Low-Resource Cross-Lingual Speech RecognitionMultimodal Embedding Integration for Cross-Lingual NER in Low-Resource LanguagesDiscrete Audio Tokens Enhance Cross-Lingual Speech Recognition in Low-Resource LanguagesAdversarial Meta Sampling for Multilingual Low-Resource Speech Recognition

XLST: Cross-lingual Self-training to Learn Multilingual Representation for Low Resource Speech Recognition

In this paper, we propose a weakly supervised multilingual representation learning framework, called

Exploiting Adapters for Cross-lingual Low-resource Speech Recognition

Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource langu

DonorRank: Donor Language Selection for Low-Resource Cross-Lingual Speech Recognition

Low-resource automatic speech recognition (ASR) commonly relies on cross-lingual transfer, where mod

Multimodal Embedding Integration for Cross-Lingual NER in Low-Resource Languages

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

Discrete Audio Tokens Enhance Cross-Lingual Speech Recognition in Low-Resource Languages

This report synthesises findings from 13 peer-reviewed papers addressing the following research ques

Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition

Low-resource automatic speech recognition (ASR) is challenging, as the low-resource target language