Related papers: Design of Soft Viterbi Algorithm Decoder Enhanced …
Analysis of vision-and-language models has revealed their brittleness under linguistic phenomena such as paraphrasing, negation, textual entailment, and word substitutions with synonyms or antonyms. While data augmentation techniques have…
In 1995, Best et al. published a formula for the exact bit error probability for Viterbi decoding of the rate R=1/2, memory m=1 (2-state) convolutional encoder with generator matrix G(D)=(1 1+D) when used to communicate over the binary…
In recent years, processing in memory (PIM) based mixedsignal designs have been proposed as energy- and area-efficient solutions with ultra high throughput to accelerate DNN computations. However, PIM designs are sensitive to imperfections…
Petabyte-scale distributed storage systems are currently transitioning to erasure codes to achieve higher storage efficiency. Classical codes like Reed-Solomon are highly sub-optimal for distributed environments due to their high overhead…
In traditional boosting algorithms, the focus on misclassified training samples emphasizes their importance based on difficulty during the learning process. While using a standard Support Vector Machine (SVM) as a weak learner in an…
This paper presents novel techniques for improving the error correction performance and reducing the complexity of coarsely quantized 5G-LDPC decoders. The proposed decoder design supports arbitrary message-passing schedules on a…
Recently, end-to-end models have been widely used in automatic speech recognition (ASR) systems. Two of the most representative approaches are connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models.…
Non-autoregressive mechanisms can significantly decrease inference time for speech transformers, especially when the single step variant is applied. Previous work on CTC alignment-based single step non-autoregressive transformer (CASS-NAT)…
The Connectionist Temporal Classification (CTC) has achieved great success in sequence to sequence analysis tasks such as automatic speech recognition (ASR) and scene text recognition (STR). These applications can use the CTC objective…
Recently, unified speech-text models, such as SpeechGPT, VioLA, and AudioPaLM, have achieved remarkable performance on various speech tasks. These models discretize speech signals into tokens (speech discretization) and use a shared…
In this paper, we investigate the problem of bit allocation in Neural Video Compression (NVC). First, we reveal that a recent bit allocation approach claimed to be optimal is, in fact, sub-optimal due to its implementation. Specifically, we…
Dual-encoder (DE) models are widely used in retrieval tasks, most commonly studied on open QA benchmarks that are often characterized by multi-class and limited training data. In contrast, their performance in multi-label and data-rich…
Quantum error correction, which utilizes logical qubits that are encoded as redundant multiple physical qubits to find and correct errors in physical qubits, is indispensable for practical quantum computing. Surface code is considered to be…
Targeting the notorious cumulative drift errors in NeRF SLAM, we propose a Semantic-guided Loop Closure using Shared Latent Code, dubbed SLC$^2$-SLAM. We argue that latent codes stored in many NeRF SLAM systems are not fully exploited, as…
In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary objective. At such extreme compression levels, codecs trained with…
Recently, the sparse vector code (SVC) is emerging as a promising solution for short-packet transmission in massive machine type communication (mMTC) as well as ultra-reliable and low-latency communication (URLLC). In the SVC process, the…
Deep polar codes, employing multi-layered polar kernel pre-transforms in series, are recently introduced variants of pre-transformed polar codes. These codes have demonstrated the ability to reduce the number of minimum weight codewords,…
We introduce an algorithm for approximating the codebook probability that is compatible with all successive cancellation (SC)-based decoding algorithms, including SC list (SCL) decoding. This approximation is based on an auxiliary…
Kitaev's toric code is arguably the most studied quantum code and is expected to be implemented in future generations of quantum computers. The renormalisation decoders introduced by Duclos-Cianci and Poulin exhibit one of the best…
NAND flash memory is ubiquitous in everyday life today because its capacity has continuously increased and cost has continuously decreased over decades. This positive growth is a result of two key trends: (1) effective process technology…