# Homophone Reveals the Truth: A Reality Check for Speech2Vec

arXiv: https://arxiv.org/abs/2209.10791 · HTML: https://mlsanity.com/paper/2209.10791/

## 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 (most cited first, 10 of 10)

- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation](https://mlsanity.com/paper/1408.3456/) (2014)
- [Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech](https://mlsanity.com/paper/1803.08976/) (2018)
- [SimVerb-3500: A Large-Scale Evaluation Set of Verb Similarity](https://mlsanity.com/paper/1608.00869/) (2016)
- [Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces](https://mlsanity.com/paper/1805.07467/) (2018)
- [Self-supervised audio representation learning for mobile devices](https://mlsanity.com/paper/1905.11796/) (2019)
- [Phonetic-and-Semantic Embedding of Spoken Words with Applications in Spoken Content Retrieval](https://mlsanity.com/paper/1807.08089/) (2018)
- [Towards Unsupervised Speech-to-Text Translation](https://mlsanity.com/paper/1811.01307/) (2018)
- [Learning Word Embeddings from Speech](https://mlsanity.com/paper/1711.01515/) (2017)

## 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.