# Multi-task self-supervised learning for Robust Speech Recognition

arXiv: https://arxiv.org/abs/2001.09239 · HTML: https://mlsanity.com/paper/2001.09239/

## Key facts

- Cited by 130 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jan 2020.

## Built on by (most cited first, 30 of 130)

- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style](https://mlsanity.com/paper/2106.04619/) (2021)
- [Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction](https://mlsanity.com/paper/2201.02184/) (2022)
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [Contrastive Learning Inverts the Data Generating Process](https://mlsanity.com/paper/2102.08850/) (2021)
- [Wav2CLIP: Learning Robust Audio Representations From CLIP](https://mlsanity.com/paper/2110.11499/) (2021)
- [SSAST: Self-Supervised Audio Spectrogram Transformer](https://mlsanity.com/paper/2110.09784/) (2021)
- [DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT](https://mlsanity.com/paper/2110.01900/) (2021)
- [BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation](https://mlsanity.com/paper/2103.06695/) (2021)
- [Contrastive Learning of Musical Representations](https://mlsanity.com/paper/2103.09410/) (2021)
- [A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding](https://mlsanity.com/paper/2111.02735/) (2021)
- [Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations](https://mlsanity.com/paper/2110.14513/) (2021)
- [UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data](https://mlsanity.com/paper/2101.07597/) (2021)
- [SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities](https://mlsanity.com/paper/2203.06849/) (2022)
- [ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers](https://mlsanity.com/paper/2204.09224/) (2022)
- [SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech](https://mlsanity.com/paper/2111.10367/) (2021)
- [mHuBERT-147: A Compact Multilingual HuBERT Model](https://mlsanity.com/paper/2406.06371/) (2024)
- [Audio Self-supervised Learning: A Survey](https://mlsanity.com/paper/2203.01205/) (2022)
- [SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data](https://mlsanity.com/paper/2209.15329/) (2022)
- [Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learning](https://mlsanity.com/paper/2303.16535/) (2023)
- [Jointly Learning Visual and Auditory Speech Representations from Raw Data](https://mlsanity.com/paper/2212.06246/) (2022)
- [UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training](https://mlsanity.com/paper/2110.05752/) (2021)
- [LiRA: Learning Visual Speech Representations from Audio through Self-supervision](https://mlsanity.com/paper/2106.09171/) (2021)
- [A Large-Scale Evaluation of Speech Foundation Models](https://mlsanity.com/paper/2404.09385/) (2024)
- [Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization](https://mlsanity.com/paper/2210.02016/) (2022)
- [Textless Speech Emotion Conversion using Discrete and Decomposed Representations](https://mlsanity.com/paper/2111.07402/) (2021)
- [SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model](https://mlsanity.com/paper/2210.00705/) (2022)

## Abstract (arXiv)

Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To take a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that combines a convolutional encoder followed by multiple neural networks, called workers, tasked to solve self-supervised problems (i.e., ones that do not require manual annotations as ground truth). PASE was shown to capture relevant speech information, including speaker voice-print and phonemes. This paper proposes PASE+, an improved version of PASE for robust speech recognition in noisy and reverberant environments. To this end, we employ an online speech distortion module, that contaminates the input signals with a variety of random disturbances. We then propose a revised encoder that better learns short- and long-term speech dynamics with an efficient combination of recurrent and convolutional networks. Finally, we refine the set of workers used in self-supervision to encourage better cooperation. Results on TIMIT, DIRHA and CHiME-5 show that PASE+ significantly outperforms both the previous version of PASE as well as common acoustic features. Interestingly, PASE+ learns transferable representations suitable for highly mismatched acoustic conditions.