# Improving Speech Representation Learning via Speech-level and Phoneme-level Masking Approach

arXiv: https://arxiv.org/abs/2210.13805 · HTML: https://mlsanity.com/paper/2210.13805/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 25 Oct 2022.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [ERNIE: Enhanced Language Representation with Informative Entities](https://mlsanity.com/paper/1905.07129/) (2019)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders](https://mlsanity.com/paper/1910.12638/) (2019)
- [TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech](https://mlsanity.com/paper/2007.06028/) (2020)
- [An Unsupervised Autoregressive Model for Speech Representation Learning](https://mlsanity.com/paper/1904.03240/) (2019)
- [Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction](https://mlsanity.com/paper/2001.10603/) (2020)
- [Audio Word2Vec: Unsupervised Learning of Audio Segment Representations using Sequence-to-sequence Autoencoder](https://mlsanity.com/paper/1603.00982/) (2016)
- [Improving Transformer-based Speech Recognition Using Unsupervised Pre-training](https://mlsanity.com/paper/1910.09932/) (2019)
- [Wav2vec-C: A Self-supervised Model for Speech Representation Learning](https://mlsanity.com/paper/2103.08393/) (2021)
- [AVQVC: One-shot Voice Conversion by Vector Quantization with applying contrastive learning](https://mlsanity.com/paper/2202.10020/) (2022)
- [Large-scale Transfer Learning for Low-resource Spoken Language Understanding](https://mlsanity.com/paper/2008.05671/) (2020)
- [TDASS: Target Domain Adaptation Speech Synthesis Framework for Multi-speaker Low-Resource TTS](https://mlsanity.com/paper/2205.11824/) (2022)

## Built on by (most cited first, 1 of 1)

- [Regularizing Learnable Feature Extraction for Automatic Speech Recognition](https://mlsanity.com/paper/2506.09804/) (2025)

## Abstract (arXiv)

Recovering the masked speech frames is widely applied in speech representation learning. However, most of these models use random masking in the pre-training. In this work, we proposed two kinds of masking approaches: (1) speech-level masking, making the model to mask more speech segments than silence segments, (2) phoneme-level masking, forcing the model to mask the whole frames of the phoneme, instead of phoneme pieces. We pre-trained the model via these two approaches, and evaluated on two downstream tasks, phoneme classification and speaker recognition. The experiments demonstrated that the proposed masking approaches are beneficial to improve the performance of speech representation.