ViP-VL achieves claimed state-of-the-art results on Vietnamese ASR, emotion recognition, dialect classification, and speaker verification via vector-quantization self-supervised pretraining on 17k hours with 8x subsampling modifications.
ViP-VL: Vietnamese Self-supervised Speech Pretraining Model with Vector-Quantization Learning
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
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.
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ViP-VL: Vietnamese Self-supervised Speech Pretraining Model with Vector-Quantization Learning
ViP-VL achieves claimed state-of-the-art results on Vietnamese ASR, emotion recognition, dialect classification, and speaker verification via vector-quantization self-supervised pretraining on 17k hours with 8x subsampling modifications.