# Comparison of Decoding Strategies for CTC Acoustic Models

arXiv: https://arxiv.org/abs/1708.04469 · HTML: https://mlsanity.com/paper/1708.04469/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Aug 2017.

## Built on by (most cited first, 13 of 13)

- [OkwuGb'e: End-to-End Speech Recognition for Fon and Igbo](https://mlsanity.com/paper/2103.07762/) (2021)
- [SlothSpeech: Denial-of-service Attack Against Speech Recognition Models](https://mlsanity.com/paper/2306.00794/) (2023)
- [ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems](https://mlsanity.com/paper/2102.08535/) (2021)
- [Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model Decoding](https://mlsanity.com/paper/2202.05209/) (2022)
- [Late multimodal fusion for image and audio music transcription](https://mlsanity.com/paper/2204.03063/) (2022)
- [Combining Unsupervised and Text Augmented Semi-Supervised Learning for Low Resourced Autoregressive Speech Recognition](https://mlsanity.com/paper/2110.15836/) (2021)
- [KinSPEAK: Improving speech recognition for Kinyarwanda via semi-supervised learning methods](https://mlsanity.com/paper/2308.11863/) (2023)
- [Leveraging Cross-Utterance Context For ASR Decoding](https://mlsanity.com/paper/2306.16903/) (2023)
- [Korean Tokenization for Beam Search Rescoring in Speech Recognition](https://mlsanity.com/paper/2203.03583/) (2022)
- [Training Autoregressive Speech Recognition Models with Limited in-domain Supervision](https://mlsanity.com/paper/2210.15135/) (2022)
- [Bidirectional Representations for Low Resource Spoken Language Understanding](https://mlsanity.com/paper/2211.14320/) (2022)
- [Unsupervised Speech Representation Pooling Using Vector Quantization](https://mlsanity.com/paper/2304.03940/) (2023)
- [LGFNet: A CTC-Guided Local-Global Fusion Framework for Single-Channel Sleep Staging](https://mlsanity.com/paper/2607.25197/) (2026)

## Abstract (arXiv)

Connectionist Temporal Classification has recently attracted a lot of interest as it offers an elegant approach to building acoustic models (AMs) for speech recognition. The CTC loss function maps an input sequence of observable feature vectors to an output sequence of symbols. Output symbols are conditionally independent of each other under CTC loss, so a language model (LM) can be incorporated conveniently during decoding, retaining the traditional separation of acoustic and linguistic components in ASR. For fixed vocabularies, Weighted Finite State Transducers provide a strong baseline for efficient integration of CTC AMs with n-gram LMs. Character-based neural LMs provide a straight forward solution for open vocabulary speech recognition and all-neural models, and can be decoded with beam search. Finally, sequence-to-sequence models can be used to translate a sequence of individual sounds into a word string. We compare the performance of these three approaches, and analyze their error patterns, which provides insightful guidance for future research and development in this important area.