mlsanityData to 7 Oct 2026

Star Temporal Classification: Sequence Classification with Partially Labeled Data

arXiv 2201.12208 ↗First posted 28 Jan 2022cs.LG cs.SD eess.AScited by 10

Not on the map. Why?

Abstract (arXiv)

We develop an algorithm which can learn from partially labeled and unsegmented sequential data. Most sequential loss functions, such as Connectionist Temporal Classification (CTC), break down when many labels are missing. We address this problem with Star Temporal Classification (STC) which uses a special star token to allow alignments which include all possible tokens whenever a token could be missing. We express STC as the composition of weighted finite-state transducers (WFSTs) and use GTN (a framework for automatic differentiation with WFSTs) to compute gradients. We perform extensive experiments on automatic speech recognition. These experiments show that STC can recover most of the performance of supervised baseline when up to 70% of the labels are missing. We also perform experiments in handwriting recognition to show that our method easily applies to other sequence classification tasks.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 19 of its 39 references that are in the map. First posted on arXiv 28 Jan 2022.

Builds on

19 of 39 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  4. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  5. 2019Reducing Transformer Depth on Demand with Structured Dropoutcited by 434
  6. 2019End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architecturescited by 120
  7. 2015EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decodingcited by 73
  8. 2020Rethinking Evaluation in ASR: Are Our Models Robust Enough?cited by 72
  9. 2020Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognitioncited by 71
  10. 2016Connectionist Temporal Modeling for Weakly Supervised Action Labelingcited by 70
  11. 2019Evaluating Sequence-to-Sequence Models for Handwritten Text Recognitioncited by 58
  12. 2016Wav2Letter: an End-to-End ConvNet-based Speech Recognition Systemcited by 43
7 more
  1. 2018wav2letter++: The Fastest Open-source Speech Recognition Systemcited by 42
  2. 2018Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networkscited by 31
  3. 2020Differentiable Weighted Finite-State Transducerscited by 22
  4. 2020Semi-Supervised Speech Recognition via Graph-based Temporal Classificationcited by 19
  5. 2021CTC Variations Through New WFST Topologiescited by 17
  6. 2019Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognitioncited by 5
  7. 2021Word Order Does Not Matter For Speech Recognitioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 1; 2025: 2; 2026: 1.

10 papers.

  1. 2022Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence taskscited by 12
  2. 2022Multi-blank Transducers for Speech Recognitioncited by 11
  3. 2023Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcriptscited by 10
  4. 2023Learning from Flawed Data: Weakly Supervised Automatic Speech Recognitioncited by 8
  5. 2023Powerful and Extensible WFST Framework for RNN-Transducer Lossescited by 7
  6. 2023Weakly-supervised forced alignment of disfluent speech using phoneme-level modelingcited by 7
  7. 2024Token-Weighted RNN-T for Learning from Flawed Datacited by 2
  8. 2025RNN-Transducer-based Losses for Speech Recognition on Noisy Targetscited by 1
  9. 2025WST: Weakly Supervised Transducer for Automatic Speech Recognitioncited by 1
  10. 2026Modeling Overlapped Speech with Shufflescited by 0