# CTC Variations Through New WFST Topologies

arXiv: https://arxiv.org/abs/2110.03098 · HTML: https://mlsanity.com/paper/2110.03098/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 6 Oct 2021.

## Builds on (most cited first, 13 of 13)

- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding](https://mlsanity.com/paper/1507.08240/) (2015)
- [Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition](https://mlsanity.com/paper/2104.01721/) (2021)
- [Why does CTC result in peaky behavior?](https://mlsanity.com/paper/2105.14849/) (2021)
- [From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition](https://mlsanity.com/paper/1910.01493/) (2019)
- [Semi-Supervised Speech Recognition via Graph-based Temporal Classification](https://mlsanity.com/paper/2010.15653/) (2020)
- [PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASR](https://mlsanity.com/paper/2005.09824/) (2020)
- [Benchmarking LF-MMI, CTC and RNN-T Criteria for Streaming ASR](https://mlsanity.com/paper/2011.04785/) (2020)
- [Faster, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces](https://mlsanity.com/paper/2005.09150/) (2020)
- [GPU-Accelerated Viterbi Exact Lattice Decoder for Batched Online and Offline Speech Recognition](https://mlsanity.com/paper/1910.10032/) (2019)
- [Advancing CTC-CRF Based End-to-End Speech Recognition with Wordpieces and Conformers](https://mlsanity.com/paper/2107.03007/) (2021)
- [A Novel Topology for End-to-end Temporal Classification and Segmentation with Recurrent Neural Network](https://mlsanity.com/paper/1912.04784/) (2019)

## Built on by (most cited first, 17 of 17)

- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks](https://mlsanity.com/paper/2210.07499/) (2022)
- [DiffVoice: Text-to-Speech with Latent Diffusion](https://mlsanity.com/paper/2304.11750/) (2023)
- [Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator](https://mlsanity.com/paper/2302.14036/) (2023)
- [Star Temporal Classification: Sequence Classification with Partially Labeled Data](https://mlsanity.com/paper/2201.12208/) (2022)
- [Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts](https://mlsanity.com/paper/2306.01031/) (2023)
- [Blank-regularized CTC for Frame Skipping in Neural Transducer](https://mlsanity.com/paper/2305.11558/) (2023)
- [Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition](https://mlsanity.com/paper/2309.15796/) (2023)
- [Powerful and Extensible WFST Framework for RNN-Transducer Losses](https://mlsanity.com/paper/2303.10384/) (2023)
- [Weakly-supervised forced alignment of disfluent speech using phoneme-level modeling](https://mlsanity.com/paper/2306.00996/) (2023)
- [Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition](https://mlsanity.com/paper/2308.06547/) (2023)
- [GPU-Accelerated WFST Beam Search Decoder for CTC-based Speech Recognition](https://mlsanity.com/paper/2311.04996/) (2023)
- [Blank Collapse: Compressing CTC emission for the faster decoding](https://mlsanity.com/paper/2210.17017/) (2022)
- [Enhancing GOP in CTC-Based Mispronunciation Detection with Phonological Knowledge](https://mlsanity.com/paper/2506.02080/) (2025)
- [RNN-Transducer-based Losses for Speech Recognition on Noisy Targets](https://mlsanity.com/paper/2504.06963/) (2025)
- [Phonetically-Augmented Discriminative Rescoring for Voice Search Error Correction](https://mlsanity.com/paper/2506.06117/) (2025)
- [Modeling Overlapped Speech with Shuffles](https://mlsanity.com/paper/2603.17769/) (2026)

## Abstract (arXiv)

This paper presents novel Weighted Finite-State Transducer (WFST) topologies to implement Connectionist Temporal Classification (CTC)-like algorithms for automatic speech recognition. Three new CTC variants are proposed: (1) the "compact-CTC", in which direct transitions between units are replaced with <epsilon> back-off transitions; (2) the "minimal-CTC", that only adds <blank> self-loops when used in WFST-composition; and (3) the "selfless-CTC" variants, which disallows self-loop for non-blank units. Compact-CTC allows for 1.5 times smaller WFST decoding graphs and reduces memory consumption by two times when training CTC models with the LF-MMI objective without hurting the recognition accuracy. Minimal-CTC reduces graph size and memory consumption by two and four times for the cost of a small accuracy drop. Using selfless-CTC can improve the accuracy for wide context window models.