# Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions

arXiv: https://arxiv.org/abs/2104.02724 · HTML: https://mlsanity.com/paper/2104.02724/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 6 Apr 2021.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [A Comparative Study on Transformer vs RNN in Speech Applications](https://mlsanity.com/paper/1909.06317/) (2019)
- [Scaling Neural Machine Translation](https://mlsanity.com/paper/1806.00187/) (2018)
- [State-of-the-art Speech Recognition With Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.01769/) (2017)
- [End-to-End Attention-based Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1508.04395/) (2015)
- [Insertion Transformer: Flexible Sequence Generation via Insertion Operations](https://mlsanity.com/paper/1902.03249/) (2019)
- [Intermediate Loss Regularization for CTC-based Speech Recognition](https://mlsanity.com/paper/2102.03216/) (2021)
- [QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions](https://mlsanity.com/paper/1910.10261/) (2019)
- [Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict](https://mlsanity.com/paper/2005.08700/) (2020)
- [Imputer: Sequence Modelling via Imputation and Dynamic Programming](https://mlsanity.com/paper/2002.08926/) (2020)
- [Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment](https://mlsanity.com/paper/2010.14233/) (2020)
- [Improved Mask-CTC for Non-Autoregressive End-to-End ASR](https://mlsanity.com/paper/2010.13270/) (2020)
- [CASS-NAT: CTC Alignment-based Single Step Non-autoregressive Transformer for Speech Recognition](https://mlsanity.com/paper/2010.14725/) (2020)
- [Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition](https://mlsanity.com/paper/2005.04862/) (2020)

## Built on by (most cited first, 30 of 61)

- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond](https://mlsanity.com/paper/2204.09269/) (2022)
- [Towards Robust Speech Representation Learning for Thousands of Languages](https://mlsanity.com/paper/2407.00837/) (2024)
- [OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification](https://mlsanity.com/paper/2402.12654/) (2024)
- [Improving Massively Multilingual ASR With Auxiliary CTC Objectives](https://mlsanity.com/paper/2302.12829/) (2023)
- [A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation](https://mlsanity.com/paper/2110.05249/) (2021)
- [Audio-Visual Efficient Conformer for Robust Speech Recognition](https://mlsanity.com/paper/2301.01456/) (2023)
- [A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks](https://mlsanity.com/paper/2305.11073/) (2023)
- [Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units](https://mlsanity.com/paper/2110.04109/) (2021)
- [HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition](https://mlsanity.com/paper/2204.06328/) (2022)
- [A context-aware knowledge transferring strategy for CTC-based ASR](https://mlsanity.com/paper/2210.06244/) (2022)
- [BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model](https://mlsanity.com/paper/2210.16663/) (2022)
- [Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates](https://mlsanity.com/paper/2109.12804/) (2021)
- [CTC-based Non-autoregressive Speech Translation](https://mlsanity.com/paper/2305.17358/) (2023)
- [Automatic Speech Recognition with BERT and CTC Transformers: A Review](https://mlsanity.com/paper/2410.09456/) (2024)
- [Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer](https://mlsanity.com/paper/2405.12983/) (2024)
- [Decoupling recognition and transcription in Mandarin ASR](https://mlsanity.com/paper/2108.01129/) (2021)
- [Distilling the Knowledge of BERT for CTC-based ASR](https://mlsanity.com/paper/2209.02030/) (2022)
- [InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR](https://mlsanity.com/paper/2204.00174/) (2022)
- [Better Intermediates Improve CTC Inference](https://mlsanity.com/paper/2204.00176/) (2022)
- [Uconv-Conformer: High Reduction of Input Sequence Length for End-to-End Speech Recognition](https://mlsanity.com/paper/2208.07657/) (2022)
- [A CTC Alignment-based Non-autoregressive Transformer for End-to-end Automatic Speech Recognition](https://mlsanity.com/paper/2304.07611/) (2023)
- [Semi-Autoregressive Streaming ASR With Label Context](https://mlsanity.com/paper/2309.10926/) (2023)
- [Improvement in Sign Language Translation Using Text CTC Alignment](https://mlsanity.com/paper/2412.09014/) (2024)
- [Improving CTC-based ASR Models with Gated Interlayer Collaboration](https://mlsanity.com/paper/2205.12462/) (2022)
- [A New Benchmark of Aphasia Speech Recognition and Detection Based on E-Branchformer and Multi-task Learning](https://mlsanity.com/paper/2305.13331/) (2023)
- [SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition](https://mlsanity.com/paper/2309.16937/) (2023)
- [Accurate Decoding of Natural Sentences from Non-Invasive Brain Recordings](https://mlsanity.com/paper/2608.18114/) (2026)
- [Memory-Efficient Training of RNN-Transducer with Sampled Softmax](https://mlsanity.com/paper/2203.16868/) (2022)
- [Neural Diarization with Non-autoregressive Intermediate Attractors](https://mlsanity.com/paper/2303.06806/) (2023)

## Abstract (arXiv)

This paper proposes a method to relax the conditional independence assumption of connectionist temporal classification (CTC)-based automatic speech recognition (ASR) models. We train a CTC-based ASR model with auxiliary CTC losses in intermediate layers in addition to the original CTC loss in the last layer. During both training and inference, each generated prediction in the intermediate layers is summed to the input of the next layer to condition the prediction of the last layer on those intermediate predictions. Our method is easy to implement and retains the merits of CTC-based ASR: a simple model architecture and fast decoding speed. We conduct experiments on three different ASR corpora. Our proposed method improves a standard CTC model significantly (e.g., more than 20 % relative word error rate reduction on the WSJ corpus) with a little computational overhead. Moreover, for the TEDLIUM2 corpus and the AISHELL-1 corpus, it achieves a comparable performance to a strong autoregressive model with beam search, but the decoding speed is at least 30 times faster.