SUPERB: Speech processing Universal PERformance Benchmark
read the original abstract
Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for various tasks with minimal adaptation. However, the speech processing community lacks a similar setup to systematically explore the paradigm. To bridge this gap, we introduce Speech processing Universal PERformance Benchmark (SUPERB). SUPERB is a leaderboard to benchmark the performance of a shared model across a wide range of speech processing tasks with minimal architecture changes and labeled data. Among multiple usages of the shared model, we especially focus on extracting the representation learned from SSL due to its preferable re-usability. We present a simple framework to solve SUPERB tasks by learning task-specialized lightweight prediction heads on top of the frozen shared model. Our results demonstrate that the framework is promising as SSL representations show competitive generalizability and accessibility across SUPERB tasks. We release SUPERB as a challenge with a leaderboard and a benchmark toolkit to fuel the research in representation learning and general speech processing.
This paper has not been read by Pith yet.
Forward citations
Cited by 18 Pith papers
-
S-JEPA : Soft Clustering Anchors for Self-Supervised Speech Representation Learning
S-JEPA uses soft GMM posteriors in a JEPA framework for self-supervised speech learning, achieving lowest WER below 90M parameters without offline re-clustering.
-
Multi-layer attentive probing improves transfer of audio representations for bioacoustics
Multi-layer attentive probing outperforms last-layer linear probing for transferring audio representations to bioacoustic tasks, indicating that standard evaluation setups may underestimate model quality.
-
MSU-Bench: Towards Speaker-Centric Understanding in Conversational Multi-Speaker Scenarios
MSU-Bench is a new two-tier benchmark covering speaker grounding to dialogue reasoning in multi-speaker conversations, with Gemini-assisted annotation and human verification.
-
End-to-End Voice Intent Recognition for Spontaneous Human-Drone Interaction with Naive Users
An end-to-end SLU architecture with frozen SSL acoustic encoder, LSTM classification head, and cross-modal distillation achieves 93% accuracy on simple commands and 82% on spontaneous speech at 7 ms latency on the new...
-
SEAM: Shortcut-Aware Real-Time Detection of Scripted vs. Spontaneous Speech for Interview Guardrails
SEAM achieves 0.971 ROC-AUC on external interview data for real-time scripted speech detection by combining shortcut-prevention data techniques with a compact audio backbone.
-
AudioMosaic: Contrastive Masked Audio Representation Learning
AudioMosaic learns general-purpose audio representations through contrastive pre-training with structured spectrogram masking, reaching state-of-the-art results on standard benchmarks and improving audio-language tasks.
-
Alethia: A Foundational Encoder for Voice Deepfakes
Alethia is a pretrained audio encoder using continuous embedding prediction and generative flow-matching reconstruction that outperforms existing speech foundation models on voice deepfake tasks with better robustness...
-
StressTest: Can YOUR Speech LM Handle the Stress?
Speech language models fail at reasoning about sentence stress but improve after fine-tuning on a new 17k-example synthetic dataset that varies stress to alter meaning.
-
SIGMA: Saliency-Guided Sparse Mask Attacks for Speech Emotion Recognition
SIGMA applies post-hoc XAI saliency maps to define reusable sparse masks for magnitude-bounded perturbations on self-supervised speech features, evaluated on IEMOCAP and TESS for competitive attack success with explan...
-
Impact Analysis of Speech Representation Learning Models for Acoustic Side-Channel Attack
KEYAC dataset benchmarks speech models for keyboard acoustic side-channel attacks, with KAN fine-tuning setting new SOTA by addressing nonlinear feature interactions.
-
Impact Analysis of Speech Representation Learning Models for Acoustic Side-Channel Attack
KEYAC dataset created; KAN fine-tuning achieves SOTA on acoustic side-channel keystroke recognition from speech representations under zero-shot and partial fine-tuning.
-
A Unified and Reproducible Experimentation Framework for Speech Understanding
SURE is a new standardized framework for evaluating and training speech foundation models and Speech LLMs to improve comparability and reproducibility under realistic conditions.
-
ULTRAS -- Unified Learning of Transformer Representations for Audio and Speech Signals
ULTRAS unifies audio and speech representation learning in a single transformer by applying patch masking to log-mel spectrograms and using a joint spectral-temporal prediction loss.
-
Joint Learning using Mixture-of-Expert-Based Representation for Speech Enhancement and Robust Emotion Recognition
Sparse MERIT uses frame-wise sparse mixture-of-experts with task-specific gating on self-supervised speech features to jointly optimize enhancement and emotion recognition, reporting gains over baselines on MSP-Podcas...
-
AVEX: What Matters for Animal Vocalization Encoding
Large empirical study finds self-supervised pre-training then supervised post-training on mixed bioacoustics and general audio data produces the strongest encoders across 26 datasets for species classification, detect...
-
MOSS-Audio Technical Report
MOSS-Audio is an audio-language model using a 12.5 Hz encoder, DeepStack cross-layer injection, time markers, and an event-preserving annotation pipeline for unified audio understanding.
-
From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning
A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.
-
Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages
A tutorial synthesizing foundations, recent models such as PALO and Maya, and low-cost methods for tri-modal multilingual AI in resource-constrained settings.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.