No article text was recorded for this version.
edge deployment constraints (computational overhead of self-supervised models)
Version 1 of 123 papers23 conceptsfrozen 2026-10-04
Papers in this version
- Blog: DAISY: Data Adaptive Self-Supervised Early Exit for Speech Representation Models
- Blog: End-to-End Integration of Speech Recognition, Dereverberation, Beamforming, and Self-Supervised Learning Representation
- Blog: Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation
- Blog: On Combining Global and Localized Self-Supervised Models of Speech
- Blog: On-device Streaming Discrete Speech Units
- Blog: Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates
- Blog: Effective and Efficient Mixed Precision Quantization of Speech Foundation Models
- Blog: LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT
- Blog: The Defender's Perspective on Automatic Speaker Verification: An Overview
- Blog: Speaker Change Detection with Weighted-sum Knowledge Distillation based on Self-supervised Pre-trained Models
- Blog: Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation
- Blog: InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training
- Blog: Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM
- Blog: A Compact End-to-End Model with Local and Global Context for Spoken Language Identification
- Blog: Adapter Learning from Pre-trained Model for Robust Spoof Speech Detection
- Blog: Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features
- Blog: DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models
- Blog: RobustDistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness
- Blog: CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders
- Blog: On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation
- Blog: How Redundant Is the Transformer Stack in Speech Representation Models?
- Blog: W2V2-Light: A Lightweight Version of Wav2vec 2.0 for Automatic Speech Recognition
- Blog: Distilling HuBERT with LSTMs via Decoupled Knowledge Distillation
History & citation
Current · Permanent link
- This direction split from Efficient Self-Supervised Speech Representation Learning (87% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_edge_deployment_constraints_computationa_0e93ed73,
title = {edge deployment constraints (computational overhead of self-supervised models)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/edge-deployment-constraints-computational-overhead-of-self-supervised-models/rdr_0e93ed73e1f24f3d99cfdc0563bbcbf7},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_edge_deployment_constraints_computationa_0e93ed73_v1,
title = {edge deployment constraints (computational overhead of self-supervised models)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/edge-deployment-constraints-computational-overhead-of-self-supervised-models/rdr_0e93ed73e1f24f3d99cfdc0563bbcbf7/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}