# Semi-Supervised Speech Recognition via Graph-based Temporal Classification

arXiv: https://arxiv.org/abs/2010.15653 · HTML: https://mlsanity.com/paper/2010.15653/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2020.

## Built on by (most cited first, 19 of 19)

- [Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition](https://mlsanity.com/paper/2106.08922/) (2021)
- [CTC Variations Through New WFST Topologies](https://mlsanity.com/paper/2110.03098/) (2021)
- [Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks](https://mlsanity.com/paper/2210.07499/) (2022)
- [Differentiable Allophone Graphs for Language-Universal Speech Recognition](https://mlsanity.com/paper/2107.11628/) (2021)
- [Star Temporal Classification: Sequence Classification with Partially Labeled Data](https://mlsanity.com/paper/2201.12208/) (2022)
- [Powerful and Extensible WFST Framework for RNN-Transducer Losses](https://mlsanity.com/paper/2303.10384/) (2023)
- [A Novel Self-training Approach for Low-resource Speech Recognition](https://mlsanity.com/paper/2308.05269/) (2023)
- [Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition](https://mlsanity.com/paper/2308.06547/) (2023)
- [Sequence Transduction with Graph-based Supervision](https://mlsanity.com/paper/2111.01272/) (2021)
- [Word Order Does Not Matter For Speech Recognition](https://mlsanity.com/paper/2110.05994/) (2021)
- [Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR](https://mlsanity.com/paper/2203.00232/) (2022)
- [Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer](https://mlsanity.com/paper/2207.14736/) (2022)
- [Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition](https://mlsanity.com/paper/2510.08047/) (2025)
- [Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models](https://mlsanity.com/paper/2111.03664/) (2021)
- [Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments](https://mlsanity.com/paper/2207.07273/) (2022)
- [InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss](https://mlsanity.com/paper/2211.00795/) (2022)
- [LESS: Large Language Model Enhanced Semi-Supervised Learning for Speech Foundational Models Using in-the-wild Data](https://mlsanity.com/paper/2506.04586/) (2025)
- [Graph Connectionist Temporal Classification for Phoneme Recognition](https://mlsanity.com/paper/2509.05399/) (2025)
- [A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition](https://mlsanity.com/paper/2609.30160/) (2026)

## Abstract (arXiv)

Semi-supervised learning has demonstrated promising results in automatic speech recognition (ASR) by self-training using a seed ASR model with pseudo-labels generated for unlabeled data. The effectiveness of this approach largely relies on the pseudo-label accuracy, for which typically only the 1-best ASR hypothesis is used. However, alternative ASR hypotheses of an N-best list can provide more accurate labels for an unlabeled speech utterance and also reflect uncertainties of the seed ASR model. In this paper, we propose a generalized form of the connectionist temporal classification (CTC) objective that accepts a graph representation of the training labels. The newly proposed graph-based temporal classification (GTC) objective is applied for self-training with WFST-based supervision, which is generated from an N-best list of pseudo-labels. In this setup, GTC is used to learn not only a temporal alignment, similarly to CTC, but also a label alignment to obtain the optimal pseudo-label sequence from the weighted graph. Results show that this approach can effectively exploit an N-best list of pseudo-labels with associated scores, considerably outperforming standard pseudo-labeling, with ASR results approaching an oracle experiment in which the best hypotheses of the N-best lists are selected manually.