mlsanityData to 14 Oct 2026

StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition

arXiv 2608.13717 ↗First posted 13 Aug 2026cs.CL eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Streaming automatic speech recognition (ASR) underperforms on domain-shifted target audio, where labeled in-domain data is costly to prepare while unlabeled audio is abundant. We present StreamHear, a semi-supervised pipeline that adapts a pretrained streaming student by fine-tuning an offline transducer teacher on the labeled training set, generating pseudo-labels on the unlabeled portion, and fine-tuning the student on the mixture. We further introduce a prior-regularized dynamic-programming realignment step that fixes chunk-level word placement using an ASR-hypothesis anchor. Across four datasets spanning financial calls, prepared read speech, and phone-quality dialogue, StreamHear consistently outperforms supervised student fine-tuning and narrows the gap to the offline teacher.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 24 references that are in the map. First posted on arXiv 13 Aug 2026.

Builds on

23 of 24 references.

References · 23

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 235
  3. 2019pyannote.audio: neural building blocks for speaker diarizationcited by 181
  4. 2019Self-Training for End-to-End Speech Recognitioncited by 129
  5. 2023Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognitioncited by 124
  6. 2020Iterative Pseudo-Labeling for Speech Recognitioncited by 83
  7. 2021SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognitioncited by 78
  8. 2020CTC-Segmentation of Large Corpora for German End-to-end Speech Recognitioncited by 76
  9. 2021Earnings-21: A Practical Benchmark for ASR in the Wildcited by 62
  10. 2020SlimIPL: Language-Model-Free Iterative Pseudo-Labelingcited by 54
  11. 2022Earnings-22: A Practical Benchmark for Accents in the Wildcited by 50
  12. 2025Voxtralcited by 43
11 more
  1. 2021Momentum Pseudo-Labeling for Semi-Supervised Speech Recognitioncited by 40
  2. 2020Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Trainingcited by 39
  3. 2020Semi-supervised ASR by End-to-end Self-trainingcited by 29
  4. 2022Pseudo Label Is Better Than Human Labelcited by 25
  5. 2023Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognitioncited by 25
  6. 2025Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLMcited by 6
  7. 2022Filter and evolve: progressive pseudo label refining for semi-supervised automatic speech recognitioncited by 4
  8. 2025Better Semi-supervised Learning for Multi-domain ASR Through Incremental Retraining and Data Filteringcited by 2
  9. 2025Unified Semi-Supervised Pipeline for Automatic Speech Recognitioncited by 2
  10. 2024Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whispercited by 1
  11. 2026ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Modelscited by 1

Built on by

Not cited yet.