Color backdoor: A robust poisoning attack in color space

W Jiang, H Li, G Xu, T Zhang - Proceedings of the IEEE/CVF …, 2023‏ - openaccess.thecvf.com
Backdoor attacks against neural networks have been intensively investigated, where the
adversary compromises the integrity of the victim model, causing it to make wrong …

Hyporadise: An open baseline for generative speech recognition with large language models

C Chen, Y Hu, CHH Yang… - Advances in …, 2023‏ - proceedings.neurips.cc
Advancements in deep neural networks have allowed automatic speech recognition (ASR)
systems to attain human parity on several publicly available clean speech datasets …

Can generative large language models perform asr error correction?

R Ma, M Qian, P Manakul, M Gales, K Knill - arxiv preprint arxiv …, 2023‏ - arxiv.org
ASR error correction is an interesting option for post processing speech recognition system
outputs. These error correction models are usually trained in a supervised fashion using the …

Large language models are efficient learners of noise-robust speech recognition

Y Hu, C Chen, CHH Yang, R Li, C Zhang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Recent advances in large language models (LLMs) have promoted generative error
correction (GER) for automatic speech recognition (ASR), which leverages the rich linguistic …

N-best t5: Robust asr error correction using multiple input hypotheses and constrained decoding space

R Ma, MJF Gales, KM Knill, M Qian - arxiv preprint arxiv:2303.00456, 2023‏ - arxiv.org
Error correction models form an important part of Automatic Speech Recognition (ASR) post-
processing to improve the readability and quality of transcriptions. Most prior works use the 1 …

A robust semantic text communication system

X Peng, Z Qin, X Tao, J Lu… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Semantic communication is increasingly viewed as a promising solution to improve the
transmission efficiency. However, semantic communications are susceptible not only to …

Softcorrect: Error correction with soft detection for automatic speech recognition

Y Leng, X Tan, W Liu, K Song, R Wang, XY Li… - proceedings of the …, 2023‏ - ojs.aaai.org
Error correction in automatic speech recognition (ASR) aims to correct those incorrect words
in sentences generated by ASR models. Since recent ASR models usually have low word …

GenTranslate: Large language models are generative multilingual speech and machine translators

Y Hu, C Chen, CHH Yang, R Li, D Zhang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Recent advances in large language models (LLMs) have stepped forward the development
of multilingual speech and machine translation by its reduced representation errors and …

Mf-aed-aec: Speech emotion recognition by leveraging multimodal fusion, asr error detection, and asr error correction

J He, X Shi, X Li, T Toda - ICASSP 2024-2024 IEEE …, 2024‏ - ieeexplore.ieee.org
The prevalent approach in speech emotion recognition (SER) involves integrating both
audio and textual information to comprehensively identify the speaker's emotion, with the …

Improving Seq2Seq grammatical error correction via decoding interventions

H Zhou, Y Liu, Z Li, M Zhang, B Zhang, C Li… - arxiv preprint arxiv …, 2023‏ - arxiv.org
The sequence-to-sequence (Seq2Seq) approach has recently been widely used in
grammatical error correction (GEC) and shows promising performance. However, the …