Probing Acoustic Representations for Phonetic Properties
Authors:
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 311-315
Abstract
Pre-trained acoustic representations such as wav2vec and DeCoAR have attained impressive word error rates (WER) for speech recognition benchmarks, particularly when labeled data is limited. But little is known about what phonetic properties these various representations acquire, and how well they encode transferable features of speech. We compare features from two conventional and four pre-trained systems in some simple frame-level phonetic classification tasks, with classifiers trained on features from one version of the TIMIT dataset and tested on features from another. All contextualized representations offered some level of transferability across domains, and models pre-trained on more audio data give better results; but overall, DeCoAR, the system with the simplest architecture, performs best. This type of benchmarking analysis can thus uncover relative strengths of various proposed acoustic representations.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Learning Problem-Agnostic Speech Representations from Multiple Self-Supervised Tasks2019
- wav2vec: Unsupervised Pre-Training for Speech Recognition2019
- Linguistic Knowledge and Transferability of Contextual Representations2019
- fairseq: A Fast, Extensible Toolkit for Sequence Modeling2019
- What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties2018
- Deep Contextualized Word Representations2018
- Audio Word2Vec: Unsupervised Learning of Audio Segment Representations Using Sequence-to-Sequence Autoencoder2016
- Deep convolutional acoustic word embeddings using word-pair side information2016
- Glove: Global Vectors for Word Representation2014
- Speaker-independent phone recognition using hidden Markov modelsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989