Integrating Self-supervised Speech Model With Pseudo Word-level Targets From Visually-grounded Speech Model

Abstract

Recent advances in self-supervised speech models have shown significant improvement in many downstream tasks. However, these models predominantly centered on frame-level training objectives, which can fall short in spoken language understanding tasks that require semantic comprehension. Existing works often rely on additional speech-text data as intermediate targets, which is costly in the real-world setting. To address this challenge, we propose Pseudo-Word HuBERT (PW-HuBERT), a framework that integrates pseudo word-level targets into the training process, where the targets are derived from a visually-ground speech model, notably eliminating the need for speech-text paired data. Our experimental results on four spoken language understanding (SLU) benchmarks suggest the superiority of our model in capturing semantic information.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyfang2024integrating

Related papers

• Hubertopic: Enhancing Semantic Representation Of Hubert Through Self-supervision Utilizing Topic Model (2023)0.00
• Word Discovery In Visually Grounded, Self-supervised Speech Models (2022)14.08
• Selective Hubert: Self-supervised Pre-training For Target Speaker In Clean And Mixture Speech (2023)7.81
• Spatial Hubert: Self-supervised Spatial Speech Representation Learning For A Single Talker From Multi-channel Audio (2023)0.00
• Ms-hubert: Mitigating Pre-training And Inference Mismatch In Masked Language Modelling Methods For Learning Speech Representations (2024)4.52
• Hubert: Self-supervised Speech Representation Learning By Masked Prediction Of Hidden Units (2021)25.30
• Multi-resolution Hubert: Multi-resolution Speech Self-supervised Learning With Masked Unit Prediction (2023)0.00
• Text-guided Hubert: Self-supervised Speech Pre-training Via Generative Adversarial Networks (2024)4.52