# TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech

arXiv: https://arxiv.org/abs/2007.06028 · HTML: https://mlsanity.com/paper/2007.06028/

## Key facts

- Cited by 188 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2020.

## Built on by (most cited first, 30 of 188)

- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT](https://mlsanity.com/paper/2110.01900/) (2021)
- [Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language](https://mlsanity.com/paper/2212.07525/) (2022)
- [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)
- [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)
- [BrainBERT: Self-supervised representation learning for intracranial recordings](https://mlsanity.com/paper/2302.14367/) (2023)
- [Assessing the State of Self-Supervised Human Activity Recognition using Wearables](https://mlsanity.com/paper/2202.12938/) (2022)
- [Audio Self-supervised Learning: A Survey](https://mlsanity.com/paper/2203.01205/) (2022)
- [Keyword Transformer: A Self-Attention Model for Keyword Spotting](https://mlsanity.com/paper/2104.00769/) (2021)
- [Detecting Corrupted Labels Without Training a Model to Predict](https://mlsanity.com/paper/2110.06283/) (2021)
- [PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition](https://mlsanity.com/paper/2106.05933/) (2021)
- [ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet](https://mlsanity.com/paper/2111.14706/) (2021)
- [Speech Emotion Recognition using Self-Supervised Features](https://mlsanity.com/paper/2202.03896/) (2022)
- [A Survey on Time-Series Pre-Trained Models](https://mlsanity.com/paper/2305.10716/) (2023)
- [SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data](https://mlsanity.com/paper/2209.15329/) (2022)
- [Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation](https://mlsanity.com/paper/2102.05766/) (2021)
- [Error Correction Code Transformer](https://mlsanity.com/paper/2203.14966/) (2022)
- [UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training](https://mlsanity.com/paper/2110.05752/) (2021)
- [On the Utility of Self-supervised Models for Prosody-related Tasks](https://mlsanity.com/paper/2210.07185/) (2022)
- [A3T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing](https://mlsanity.com/paper/2203.09690/) (2022)
- [A Large-Scale Evaluation of Speech Foundation Models](https://mlsanity.com/paper/2404.09385/) (2024)
- [An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition](https://mlsanity.com/paper/2110.04590/) (2021)
- [VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning](https://mlsanity.com/paper/2211.11275/) (2022)
- [Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration](https://mlsanity.com/paper/2306.06232/) (2023)

## Abstract (arXiv)

We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction, autoregressive prediction, or masked reconstruction. Unlike previous methods, we use alteration along three orthogonal axes to pre-train Transformer Encoders on a large amount of unlabeled speech. The model learns through the reconstruction of acoustic frames from their altered counterpart, where we use a stochastic policy to alter along various dimensions: time, frequency, and magnitude. TERA can be used for speech representations extraction or fine-tuning with downstream models. We evaluate TERA on several downstream tasks, including phoneme classification, keyword spotting, speaker recognition, and speech recognition. We present a large-scale comparison of various self-supervised models. TERA achieves strong performance in the comparison by improving upon surface features and outperforming previous models. In our experiments, we study the effect of applying different alteration techniques, pre-training on more data, and pre-training on various features. We analyze different model sizes and find that smaller models are strong representation learners than larger models, while larger models are more effective for downstream fine-tuning than smaller models. Furthermore, we show the proposed method is transferable to downstream datasets not used in pre-training.