Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 16 of its 25 references that are in the map. First posted on arXiv 20 Sep 2026.
Builds on
16 of 25 references.
References · 16
- 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
- 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 501
- 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 400
- 2026Qwen3-ASR Technical Reportcited by 118
- 2019Dynamic Curriculum Learning for Imbalanced Data Classificationcited by 93
- 2025NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizationscited by 15
- 2025NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speechcited by 14
- 2025A Scalable Pipeline for Enabling Non-Verbal Speech Generation and Understandingcited by 11
- 2025SynParaSpeech: Automated Synthesis of Paralinguistic Datasets for Speech Generation and Understandingcited by 6
- 2025MNV-17: A High-Quality Performative Mandarin Dataset for Nonverbal Vocalization Recognition in Speechcited by 6
- 2026WavBench: Benchmarking Reasoning, Colloquialism, and Paralinguistics for End-to-End Spoken Dialogue Modelscited by 6
- 2026Preference Optimization for Non-Verbal Vocalization Synthesiscited by 2
4 more
- 2026Preference Optimization with LALM Feedback for Continuous Autoregressive Non-Verbal Vocalization Generationcited by 2
- 2026WESR: Scaling and Evaluating Word-level Event-Speech Recognitioncited by 1
- 2026Source-Adaptive Data Curation for Bilingual NVV-Aware ASRcited by 1
- 2026NVV-Locator: From Transcript Tags to Acoustic Boundaries for Fine-Grained Nonverbal Vocalization Groundingcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.