mlsanityData to 14 Oct 2026

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

arXiv 2501.17615 ↗First posted 29 Jan 2025cs.CL cs.SD eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 29 Jan 2025.

Builds on

24 of 35 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  5. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  6. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  7. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  8. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  9. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  10. 2019Cross-lingual Language Model Pretrainingcited by 1,090
  11. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  12. 2017Word Translation Without Parallel Datacited by 487
12 more
  1. 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 273
  2. 2015End-to-End Attention-based Large Vocabulary Speech Recognitioncited by 151
  3. 2021Unsupervised Speech Recognitioncited by 148
  4. 2018A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddingscited by 146
  5. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 125
  6. 2021A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understandingcited by 82
  7. 2020CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpuscited by 57
  8. 2015THCHS-30 : A Free Chinese Speech Corpuscited by 43
  9. 2021Exploiting Adapters for Cross-lingual Low-resource Speech Recognitioncited by 35
  10. 2020Towards Zero-shot Learning for Automatic Phonemic Transcriptioncited by 14
  11. 2018Effectiveness of Hierarchical Softmax in Large Scale Classification Taskscited by 8
  12. 2022Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognitioncited by 7

Built on by

Not cited yet.