mlsanityData to 7 Oct 2026

Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models

arXiv 1811.00403 ↗First posted 1 Nov 2018cs.CL cs.LG cs.SDcited by 29

Not on the map. Why?

Abstract (arXiv)

We investigate unsupervised models that can map a variable-duration speech segment to a fixed-dimensional representation. In settings where unlabelled speech is the only available resource, such acoustic word embeddings can form the basis for "zero-resource" speech search, discovery and indexing systems. Most existing unsupervised embedding methods still use some supervision, such as word or phoneme boundaries. Here we propose the encoder-decoder correspondence autoencoder (EncDec-CAE), which, instead of true word segments, uses automatically discovered segments: an unsupervised term discovery system finds pairs of words of the same unknown type, and the EncDec-CAE is trained to reconstruct one word given the other as input. We compare it to a standard encoder-decoder autoencoder (AE), a variational AE with a prior over its latent embedding, and downsampling. EncDec-CAE outperforms its closest competitor by 24% relative in average precision on two languages in a word discrimination task.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 7; 2023: 9; 2024: 4; 2025: 1.

29 papers.

Sort:

  1. 2022Self-Supervised Speech Representation Learning: A Reviewcited by 258
  2. 2022Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Modelscited by 21
  3. 2021Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptationcited by 19
  4. 2023Generative Spoken Language Model based on continuous word-sized audio tokenscited by 19
  5. 2023SD-HuBERT: Sentence-Level Self-Distillation Induces Syllabic Organization in HuBERTcited by 13
  6. 2022DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexiconcited by 12
  7. 2022A Brief Overview of Unsupervised Neural Speech Representation Learningcited by 9
  8. 2021Do Acoustic Word Embeddings Capture Phonological Similarity? An Empirical Studycited by 8
  9. 2021How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddingscited by 8
  10. 2021Double Articulation Analyzer with Prosody for Unsupervised Word and Phoneme Discoverycited by 7
  11. 2021Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource languagecited by 7
  12. 2021Interpreting intermediate convolutional layers of generative CNNs trained on waveformscited by 6
17 more
  1. 2021A phonetic model of non-native spoken word processingcited by 5
  2. 2021Unsupervised Automatic Speech Recognition: A Reviewcited by 5
  3. 2023Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahilicited by 5
  4. 2023Visually grounded few-shot word learning in low-resource settingscited by 4
  5. 2024SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representationscited by 3
  6. 2024Improving Acoustic Word Embeddings through Correspondence Training of Self-supervised Speech Representationscited by 3
  7. 2024Visually Grounded Speech Models have a Mutual Exclusivity Biascited by 3
  8. 2022Integrating Form and Meaning: A Multi-Task Learning Model for Acoustic Word Embeddingscited by 2
  9. 2022Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddingscited by 2
  10. 2023Analyzing the Representational Geometry of Acoustic Word Embeddingscited by 2
  11. 2023Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Poolingcited by 2
  12. 2023Leveraging multilingual transfer for unsupervised semantic acoustic word embeddingscited by 2
  13. 2024LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Taskscited by 2
  14. 2022Learning Phone Recognition from Unpaired Audio and Phone Sequences Based on Generative Adversarial Networkcited by 1
  15. 2023Visually grounded few-shot word acquisition with fewer shotscited by 1
  16. 2023XLS-R fine-tuning on noisy word boundaries for unsupervised speech segmentation into wordscited by 1
  17. 2025Joint Multimodal Contrastive Learning for Robust Spoken Term Detection and Keyword Spottingcited by 0