Symbol-Level Deep Learning-Based Decoders for Concatenated Codes Over Insertion/Deletion Channels

Synchronization errors, such as insertions and deletions, pose significant challenges in communication and storage systems, including DNA data storage. Among different alternatives, serially concatenated coding schemes, where a powerful outer code is concatenated with an inner marker code, have proven effective in mitigating such errors. A common method of decoding the inner marker code is to employ the forward-backward algorithm implementing bitwise or symbolwise maximum a posteriori (MAP) detection. Recently, bit-level deep-learning based solutions have also been proposed for decoding marker codes. In this paper, we consider symbol-level deep-learning based decoders, which exploit correlations among adjacent bits to improve the decoding performance, and develop new channel detection algorithms. Unlike existing symbol-level MAP decoding approaches that can combine only two or three consecutive bits, the proposed deep-learning methods extend well beyond this limit, and achieve improved error correction performance. We also develop deep-learning based decoders for insertion/deletion channels further exacerbated by intersymbol interference, motivated by bit-patterned media recording channels and nanopore sequencing. Extensive numerical results show that the proposed symbol-level deep-learning architectures are highly effective for communication over insertion/deletion channels.

• Publication year

  2026

• Venue

  IEEE Transactions on Communications

• Publication date

  Unknown publication date

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/TCOMM.2026.3655750
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Transformer-Based Decoding in Concatenated Coding Schemes Under Synchronization Errors

  2025cited by this paper
• Disturbance-based Discretization, Differentiable IDS Channel, and an IDS-Correcting Code for DNA-based Storage

  2024cited by this paper
• CrossMPT: Cross-attention Message-Passing Transformer for Error Correcting Codes

  2024cited by this paper
• A Deep Learning Based Decoder for Concatenated Coding Over Deletion Channels

  2024influential reference
• A Foundation Model for Error Correction Codes

  2024cited by this paper
• Learning Linear Block Error Correction Codes

  2024cited by this paper
• Deep Learning-Based Detection for Marker Codes Over Insertion and Deletion Channels

  2024influential reference
• Accelerating Error Correction Code Transformers

  2024cited by this paper
• Boosting Learning for LDPC Codes to Improve the Error-Floor Performance

  2023cited by this paper
• Graph Neural Networks for Channel Decoding

  2022cited by this paper
• Windowed-Based Synchronization Error-Correction for Spatially Coupled Codes

  2022cited by this paper
• Error Correction Code Transformer

  2022cited by this paper
• A Modified Q-Learning Algorithm for Rate-Profiling of Polarization Adjusted Convolutional (PAC) Codes

  2021cited by this paper
• Construction of Polar Codes with Reinforcement Learning

  2020cited by this paper
• How Does Learning Rate Decay Help Modern Neural Networks

  2019cited by this paper
• DEEPTURBO: Deep Turbo Decoder

  2019cited by this paper
• Nanopore DNA Sequencing Channel Modeling

  2018cited by this paper
• On deep learning-based channel decoding

  2017influential reference
• DNA-Based Storage: Trends and Methods

  2015cited by this paper
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

  2015cited by this paper
• Upper Bounds on the Capacity of Deletion Channels Using Channel Fragmentation

  2015cited by this paper
• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

  2014influential reference
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Coding for Insertion/Deletion Channels

  2012cited by this paper
• Bounds on the Capacity of Channels with Insertions, Deletions and Substitutions

  2011cited by this paper
• Symbol-Level Synchronization and LDPC Code Design for Insertion/Deletion Channels

  2011influential reference
• Bounds on the Capacity of Random Insertion and Deletion-Additive Noise Channels

  2011cited by this paper
• Achievable information rates for channels with insertions, deletions, and intersymbol interference with i.i.d. inputs

  2010influential reference
• Upper Bounding the Deletion Channel Capacity by Auxiliary Memoryless Channels

  2009cited by this paper
• Novel Bounds on the Capacity of the Binary Deletion Channel

  2008cited by this paper
• Bit-Patterned Media With Written-In Errors: Modeling, Detection, and Theoretical Limits

  2007cited by this paper
• Recording potential of bit-patterned media

  2006cited by this paper
• Convolutional codes for channels with substitutions, insertions, and deletions

  2002cited by this paper
• Insertion /deletion correcting coding schemes based on convolution coding

  2002cited by this paper
• Reliable communication over channels with insertions, deletions, and substitutions

  2001cited by this paper
• Codes for Channels with Insertions, Deletions and Substitutions

  2000cited by this paper
• Encyclopedia of Sparse Graph Codes

  1999cited by this paper
• Bidirectional recurrent neural networks

  1997cited by this paper
• Patterned Media: A Viable Route to 50 Gbit/in2 and Up for Magnetic Recording?

  1997cited by this paper
• Insertion/deletion correction with spectral nulls

  1997cited by this paper
• SEQUENTIAL DECODING FOR BINARY CHANNELS WITH NOISE AND SYNCHRONIZATION ERRORS

  1961cited by this paper

• No citing papers are available for this paper.