Can contextual biasing remain effective with Whisper and GPT-2?
End-to-end automatic speech recognition (ASR) and large language models, such as
Whisper and GPT-2, have recently been scaled to use vast amounts of training data. Despite …
Whisper and GPT-2, have recently been scaled to use vast amounts of training data. Despite …
Foundationtts: Text-to-speech for asr customization with generative language model
Neural text-to-speech (TTS) generally consists of cascaded architecture with separately
optimized acoustic model and vocoder, or end-to-end architecture with continuous mel …
optimized acoustic model and vocoder, or end-to-end architecture with continuous mel …
Improving contextual spelling correction by external acoustics attention and semantic aware data augmentation
We previously proposed contextual spelling correction (CSC) to correct the output of end-to-
end (E2E) automatic speech recognition (ASR) models with contextual information such as …
end (E2E) automatic speech recognition (ASR) models with contextual information such as …
Contextual Spelling Correction with Large Language Models
Contextual Spelling Correction (CSC) models are used to improve automatic speech
recognition (ASR) quality given userspecific context. Typically, context is modeled as a large …
recognition (ASR) quality given userspecific context. Typically, context is modeled as a large …
Automatic real-word error correction in persian text
Automatic spelling correction stands as a pivotal challenge within the ambit of natural
language processing (NLP), demanding nuanced solutions. Traditional spelling correction …
language processing (NLP), demanding nuanced solutions. Traditional spelling correction …
Spellmapper: A non-autoregressive neural spellchecker for asr customization with candidate retrieval based on n-gram mappings
A Antonova, E Bakhturina, B Ginsburg - arXiv preprint arXiv:2306.02317, 2023 - arxiv.org
Contextual spelling correction models are an alternative to shallow fusion to improve
automatic speech recognition (ASR) quality given user vocabulary. To deal with large user …
automatic speech recognition (ASR) quality given user vocabulary. To deal with large user …
Contextualized Automatic Speech Recognition With Attention-Based Bias Phrase Boosted Beam Search
End-to-end (E2E) automatic speech recognition (ASR) methods exhibit remarkable
performance. However, since the performance of such methods is intrinsically linked to the …
performance. However, since the performance of such methods is intrinsically linked to the …
ED-CEC: Improving rare word recognition using asr postprocessing based on error detection and context-aware error correction
Automatic speech recognition (ASR) systems often encounter difficulties in accurately
recognizing rare words, leading to errors that can have a negative impact on downstream …
recognizing rare words, leading to errors that can have a negative impact on downstream …
Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation
Existing research suggests that automatic speech recognition (ASR) models can benefit
from additional contexts (eg, contact lists, user specified vocabulary). Rare words and …
from additional contexts (eg, contact lists, user specified vocabulary). Rare words and …
Improving the quality of Persian clinical text with a novel spelling correction system
SMS Dashti, SF Dashti - BMC Medical Informatics and Decision Making, 2024 - Springer
Background The accuracy of spelling in Electronic Health Records (EHRs) is a critical factor
for efficient clinical care, research, and ensuring patient safety. The Persian language, with …
for efficient clinical care, research, and ensuring patient safety. The Persian language, with …