mlsanityData to 13 Oct 2026

Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition

arXiv 2204.03855 ↗First posted 8 Apr 2022eess.AS cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Low-resource speech recognition has been long-suffering from insufficient training data. In this paper, we propose an approach that leverages neighboring languages to improve low-resource scenario performance, founded on the hypothesis that similar linguistic units in neighboring languages exhibit comparable term frequency distributions, which enables us to construct a Huffman tree for performing multilingual hierarchical Softmax decoding. This hierarchical structure enables cross-lingual knowledge sharing among similar tokens, thereby enhancing low-resource training outcomes. Empirical analyses demonstrate that our method is effective in improving the accuracy and efficiency of low-resource speech recognition.

Key facts. Cited by 7 papers in the map (data through 13 Oct 2026). Builds on 20 of its 33 references that are in the map. First posted on arXiv 8 Apr 2022.

Builds on

20 of 33 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,106
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,870
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,467
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,844
  5. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,625
  6. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,366
  7. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 366
  8. 2015End-to-End Attention-based Large Vocabulary Speech Recognitioncited by 148
  9. 2021Unsupervised Speech Recognitioncited by 147
  10. 2018A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddingscited by 146
  11. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 123
  12. 2021A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understandingcited by 82
8 more
  1. 2020CoVoST 2 and Massively Multilingual Speech-to-Text Translationcited by 74
  2. 2020CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpuscited by 57
  3. 2015THCHS-30 : A Free Chinese Speech Corpuscited by 43
  4. 2021Exploiting Adapters for Cross-lingual Low-resource Speech Recognitioncited by 34
  5. 2020Towards Zero-shot Learning for Automatic Phonemic Transcriptioncited by 14
  6. 2021Multilingual and crosslingual speech recognition using phonological-vector based phone embeddingscited by 11
  7. 2018Effectiveness of Hierarchical Softmax in Large Scale Classification Taskscited by 8
  8. 2017Automatic Speech Recognition with Very Large Conversational Finnish and Estonian Vocabulariescited by 5

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 3; 2026: 1.

7 papers.

  1. 2023Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecyclecited by 13
  2. 2024Phonetic Segmentation of the UCLA Phonetics Lab Archivecited by 9
  3. 2023Language-universal phonetic encoder for low-resource speech recognitioncited by 2
  4. 2025BLR-MoE: Boosted Language-Routing Mixture of Experts for Domain-Robust Multilingual E2E ASRcited by 2
  5. 2025CUPE: Contextless Universal Phoneme Encoder for Language-Agnostic Speech Processingcited by 1
  6. 2025Cross-lingual Embedding Clustering for Hierarchical Softmax in Low-Resource Multilingual Speech Recognitioncited by 0
  7. 2026Improving low-resource ASR using bilingual fine-tuning with language identification: a cross-linguistic evaluationcited by 0