mlsanityData to 14 Oct 2026

Homophone Reveals the Truth: A Reality Check for Speech2Vec

arXiv 2209.10791 ↗First posted 22 Sep 2022cs.CL cs.SD eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Generating spoken word embeddings that possess semantic information is a fascinating topic. Compared with text-based embeddings, they cover both phonetic and semantic characteristics, which can provide richer information and are potentially helpful for improving ASR and speech translation systems. In this paper, we review and examine the authenticity of a seminal work in this field: Speech2Vec. First, a homophone-based inspection method is proposed to check the speech embeddings released by the author of Speech2Vec. There is no indication that these embeddings are generated by the Speech2Vec model. Moreover, through further analysis of the vocabulary composition, we suspect that a text-based model fabricates these embeddings. Finally, we reproduce the Speech2Vec model, referring to the official code and optimal settings in the original paper. Experiments showed that this model failed to learn effective semantic embeddings. In word similarity benchmarks, it gets a correlation score of 0.08 in MEN and 0.15 in WS-353-SIM tests, which is over 0.5 lower than those described in the original paper. Our data and code are available.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 27 references that are in the map. First posted on arXiv 22 Sep 2022.

Builds on

10 of 27 references.

References · 10

  1. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  2. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  3. 2014SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimationcited by 172
  4. 2018Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speechcited by 52
  5. 2016SimVerb-3500: A Large-Scale Evaluation Set of Verb Similaritycited by 44
  6. 2018Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spacescited by 34
  7. 2019Self-supervised audio representation learning for mobile devicescited by 17
  8. 2018Phonetic-and-Semantic Embedding of Spoken Words with Applications in Spoken Content Retrievalcited by 11
  9. 2018Towards Unsupervised Speech-to-Text Translationcited by 6
  10. 2017Learning Word Embeddings from Speechcited by 3

Built on by

Not cited yet.