Papers
arxiv:2606.10360

ViP-VL: Vietnamese Self-supervised Speech Pretraining Model with Vector-Quantization Learning

Published on Jun 10
Authors:
,
,
,
,
,
,
,

Abstract

ViP-VL is an efficient Vietnamese self-supervised speech pretraining model that uses vector-quantization learning with acoustic stacking and receptive field alignment for enhanced representation robustness.

We present ViP-VL, an efficient Vietnamese Self-supervised speech Pretraining model leveraging Vector-quantization Learning. To bridge the gap between high-resolution audio and efficient processing, ViP-VL incorporates Acoustic Stacking and Receptive Field Alignment to enable a synchronized 8x subsampling rate within the ChunkFormer architecture, while further enhancing representation robustness through a specialized Mask Selection Strategy during pretraining on the BEST-RQ framework. Pretrained on 17,000 hours of unlabeled Vietnamese speech, our model establishes new state-of-the-art results across four major downstream tasks: Automatic Speech Recognition, Speech Emotion Recognition, Dialect Classification, and Speaker Verification. To facilitate future research and the development of high-performance Vietnamese speech technologies, we publicly release our pretrained weights and implementation at github.com/khanld/chunkformer.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2606.10360
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2606.10360 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2606.10360 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.