# Ask2Mask: Guided Data Selection for Masked Speech Modeling

arXiv: https://arxiv.org/abs/2202.12719 · HTML: https://mlsanity.com/paper/2202.12719/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 24 Feb 2022.

## Builds on (most cited first, 22 of 22)

- [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)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [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)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [Selection via Proxy: Efficient Data Selection for Deep Learning](https://mlsanity.com/paper/1906.11829/) (2019)
- [ERNIE: Enhanced Representation through Knowledge Integration](https://mlsanity.com/paper/1904.09223/) (2019)
- [Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss](https://mlsanity.com/paper/2002.02562/) (2020)
- [Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2010.10504/) (2020)
- [Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training](https://mlsanity.com/paper/2104.01027/) (2021)
- [Improved Noisy Student Training for Automatic Speech Recognition](https://mlsanity.com/paper/2005.09629/) (2020)
- [CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings](https://mlsanity.com/paper/2004.09249/) (2020)
- [Self-Training for End-to-End Speech Recognition](https://mlsanity.com/paper/1909.09116/) (2019)
- [Self-training and Pre-training are Complementary for Speech Recognition](https://mlsanity.com/paper/2010.11430/) (2020)
- [SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network](https://mlsanity.com/paper/2104.02133/) (2021)
- [Rethinking Evaluation in ASR: Are Our Models Robust Enough?](https://mlsanity.com/paper/2010.11745/) (2020)
- [PMI-Masking: Principled masking of correlated spans](https://mlsanity.com/paper/2010.01825/) (2020)
- [Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning](https://mlsanity.com/paper/2007.01293/) (2020)
- [Semantic Mask for Transformer based End-to-End Speech Recognition](https://mlsanity.com/paper/1912.03010/) (2019)

## Built on by (most cited first, 3 of 3)

- [Guided Masked Self-Distillation Modeling for Distributed Multimedia Sensor Event Analysis](https://mlsanity.com/paper/2404.08264/) (2024)
- [Decoupled Structure for Improved Adaptability of End-to-End Models](https://mlsanity.com/paper/2308.13345/) (2023)
- [O-1: Self-training with Oracle and 1-best Hypothesis](https://mlsanity.com/paper/2308.07486/) (2023)

## Abstract (arXiv)

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems, they have one major limitation. They treat all unsupervised speech samples with equal weight, which hinders learning as not all samples have relevant information to learn meaningful representations. In this work, we address this limitation. We propose ask2mask (ATM), a novel approach to focus on specific samples during MSM pre-training. ATM employs an external ASR model or textitscorer to weight unsupervised input samples in two different ways: 1) A fine-grained data selection is performed by masking over the highly confident input frames as chosen by the scorer. This allows the model to learn meaningful representations. 2) ATM is further extended to focus at utterance-level by weighting the final MSM loss with the utterance-level confidence score. We conduct fine-tuning experiments on two well-benchmarked corpora: LibriSpeech (matching the pre-training data) and Commonvoice, TED-LIUM, AMI and CHiME-6 (not matching the pre-training data). The results substantiate the efficacy of ATM on significantly improving the recognition performance under mismatched conditions (up to 11.6% relative over published results and upto 4.46% relative over our internal baseline) while still yielding modest improvements under matched conditions.