vix.ing · top · new · best · stats · spec

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation

2025/05/26 by Prabash Reddy Male, Male, Prabash Reddy, Swayambhu Nath Ray +20 · 2 citations
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #Speech Recognition and Synthesis #Speech and Audio Processing #Speech and dialogue systems #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2505.19774

openalex publication_date 2025/05/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recent advancements in speech encoders have drawn attention due to their integration with Large Language Models for various speech tasks. While most research has focused on either causal or full-context speech encoders, there's limited exploration to effectively handle both streaming and non-streaming applications, while achieving state-of-the-art performance. We introduce DuRep, a Dual-mode Speech Representation learning setup, which enables a single speech encoder to function efficiently in both offline and online modes without additional parameters or mode-specific adjustments, across downstream tasks. DuRep-200M, our 200M parameter dual-mode encoder, achieves 12% and 11.6% improvements in streaming and non-streaming modes, over baseline encoders on Multilingual ASR. Scaling this approach to 2B parameters, DuRep-2B sets new performance benchmarks across ASR and non-ASR tasks. Our analysis reveals interesting trade-offs between acoustic and semantic information across encoder layers.

Cited by

Related