Learning Word Embeddings: Unsupervised Methods for Fixed-size Representations of Variable-length Speech Segments

By Nils Holzenberger, Mingxing Du, Julien Karadayi, Rachid Riad, Emmanuel Dupoux. 2018

36 citations recorded by the source corpus.

Fixed-length embeddings of words are very useful for a variety of tasks in speech and language processing. Here we systematically explore two methods of computing fixed-length embeddings for variable-length sequences. We evaluate their susceptibility to phonetic and speaker-specific variability on English, a high resource language and Xitsonga, a low resource language, using two evaluation metrics: ABX word discrimination and ROC-AUC on same-different phoneme n-grams. We show that a simple downsampling method supplemented with length information can outperform the variable-length input feature representation on both evaluations. Recurrent autoencoders, trained without supervision, can yield even better results at the expense of increased computational complexity.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. James R. Glass
2. Wei-Ning Hsu
3. David F. Harwath
4. Hung-yi Lee
5. Karen Livescu
6. Abdel-rahman Mohamed
7. Dong Yu
8. Jinyu Li

In Representation & Self-Supervised Learning

1. James R. Glass
2. David F. Harwath
3. Wei-Ning Hsu
4. Herman Kamper
5. Hung-yi Lee
6. Karen Livescu
7. Abdel-rahman Mohamed
8. Yu-An Chung

In Speech & Audio

1. James R. Glass
2. Wei-Ning Hsu
3. David F. Harwath
4. Karen Livescu
5. Herman Kamper
6. Hung-yi Lee
7. Abdel-rahman Mohamed
8. Yu-An Chung

Citations in the corpus

• Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech (2019, methodology): “Deep neural network models have been successfully used to learn powerful speech representations using weakly or unsupervised objectives (Thiolliere et al., 2015; Kamper et al., 2015; Hsu et al., 2017a;b; Hsu & Glass, 2018; Holzenberger et al., 2018; Milde & Biemann, 2018; van den Oord et al., 2018; ”
• Self-Supervised Speech Representation Learning: A Review (2022, methodology): “Later work used variants of neural autoencoders [118], [200], [201], [202].”
• A Brief Overview of Unsupervised Neural Speech Representation Learning (2022, unknown): “Similar RNN-based autoencoders have also been explored (Kamper 2019; Holzenberger et al. 2018).”
• Multimodal and Multilingual Embeddings for Large-Scale Speech Mining (2021, methodology): “Holzenberger et al. (2018); Chung et al. (2016) introduced an auto-encoder approach based on recurrent neural networks to extract a fixed-size vector between the encoder and the decoder.”
• Semantic Query-by-example Speech Search Using Visual Grounding (2019, methodology): “Various acoustic embedding functions have been proposed, with neural models used in several studies [16, 18, 23–30].”