mlsanityData to 14 Oct 2026

Spoken Word2Vec: Learning Skipgram Embeddings from Speech

arXiv 2311.09319 ↗First posted 15 Nov 2023cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Text word embeddings that encode distributional semantics work by modeling contextual similarities of frequently occurring words. Acoustic word embeddings, on the other hand, typically encode low-level phonetic similarities. Semantic embeddings for spoken words have been previously explored using analogous algorithms to Word2Vec, but the resulting vectors still mainly encoded phonetic rather than semantic features. In this paper, we examine the assumptions and architectures used in previous works and show experimentally how shallow skipgram-like algorithms fail to encode distributional semantics when the input units are acoustically correlated. We illustrate the potential of an alternative deep end-to-end variant of the model and examine the effects on the resulting embeddings, showing positive results of semantic relatedness in the embedding space.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 28 references that are in the map. First posted on arXiv 15 Nov 2023.

Builds on

20 of 28 references.

References · 20

  1. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  4. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  5. 2018Deep contextualized word representationscited by 2,290
  6. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  7. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 666
  8. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 616
  9. 2021Generative Spoken Language Modeling from Raw Audiocited by 340
  10. 2020Byte Pair Encoding is Suboptimal for Language Model Pretrainingcited by 192
  11. 2021Unsupervised Speech Recognitioncited by 148
  12. 2018Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speechcited by 52
8 more
  1. 2016Audio Word2Vec: Unsupervised Learning of Audio Segment Representations using Sequence-to-sequence Autoencodercited by 34
  2. 2020A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddingscited by 12
  3. 2018Phonetic-and-Semantic Embedding of Spoken Words with Applications in Spoken Content Retrievalcited by 11
  4. 2020Multilingual acoustic word embedding models for processing zero-resource languagescited by 9
  5. 2017Unsupervised Word Mapping Using Structural Similarities in Monolingual Embeddingscited by 7
  6. 2018Learning Acoustic Word Embeddings with Temporal Context for Query-by-Example Speech Searchcited by 7
  7. 2015Alternative structures for character-level RNNscited by 5
  8. 2021Unsupervised Automatic Speech Recognition: A Reviewcited by 5

Built on by

Not cited yet.