Abstract
Non-verbal vocalizations (NVVs) carry important paralinguistic information but are often omitted by conventional automatic speech recognition (ASR) systems. The ISCSLP NVVSpeech Challenge requires joint transcription of lexical content and 16 NVV categories under limited and highly imbalanced supervision. We present a data-centric NVV-aware ASR pipeline based on cross-dataset label harmonization and a two-stage sampling schedule. We map heterogeneous source labels to the official taxonomy and exclude samples without a reliable mapping. Our schedule first uses square-root category sampling to moderate the long-tailed distribution and then applies uniform-category fine-tuning. On a fixed local validation split, square-root category sampling performs best among the tested single-stage settings. The final two-stage system obtains an official score of 63.86 and ranks fourth in Track 1.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Jia, S., Ma, J., Li, Y., Luo, D., Tian, B., Lu, H., Ren, W., Chen, Y., Liu, H., Feng, S., Xie, L., & Xue, L. (2026). Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge. https://omanscience.com/en/articles/long-tail-rebalancing-for-non-verbal-vocalization-aware-asr-a-track-1-system-for-the-nvvspeech-challenge
MLA 9
Jia, Shangyue, et al. "Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge." https://omanscience.com/en/articles/long-tail-rebalancing-for-non-verbal-vocalization-aware-asr-a-track-1-system-for-the-nvvspeech-challenge.
Chicago (author–date)
Jia, Shangyue, Jingru Ma, Yangzhuo Li, Daoping Luo, Bowen Tian, Hanchen Lu, Wenze Ren, Yunxiang Chen, Houdun Liu, Su Feng, Lei Xie, and Liumeng Xue. 2026. "Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge." https://omanscience.com/en/articles/long-tail-rebalancing-for-non-verbal-vocalization-aware-asr-a-track-1-system-for-the-nvvspeech-challenge.
Harvard
Jia, S., Ma, J., Li, Y., Luo, D., Tian, B., Lu, H., Ren, W., Chen, Y., Liu, H., Feng, S., Xie, L. and Xue, L. (2026) 'Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge', Available at: https://omanscience.com/en/articles/long-tail-rebalancing-for-non-verbal-vocalization-aware-asr-a-track-1-system-for-the-nvvspeech-challenge.
Vancouver
Jia S, Ma J, Li Y, Luo D, Tian B, Lu H, et al. Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge. https://omanscience.com/en/articles/long-tail-rebalancing-for-non-verbal-vocalization-aware-asr-a-track-1-system-for-the-nvvspeech-challenge
IEEE
S. Jia, J. Ma, Y. Li, D. Luo, B. Tian, H. Lu, W. Ren, Y. Chen, H. Liu, S. Feng, L. Xie, and L. Xue, "Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge," https://omanscience.com/en/articles/long-tail-rebalancing-for-non-verbal-vocalization-aware-asr-a-track-1-system-for-the-nvvspeech-challenge.