Can generative large language models perform asr error correction?
ASR error correction continues to serve as an important part of post-processing for speech
recognition systems. Traditionally, these models are trained with supervised training using …
recognition systems. Traditionally, these models are trained with supervised training using …
Fastcorrect 2: Fast error correction on multiple candidates for automatic speech recognition
Error correction is widely used in automatic speech recognition (ASR) to post-process the
generated sentence, and can further reduce the word error rate (WER). Although multiple …
generated sentence, and can further reduce the word error rate (WER). Although multiple …
Translation-enhanced multilingual text-to-image generation
Research on text-to-image generation (TTI) still predominantly focuses on the English
language due to the lack of annotated image-caption data in other languages; in the long …
language due to the lack of annotated image-caption data in other languages; in the long …
ASR Error Correction using Large Language Models
Error correction (EC) models play a crucial role in refining Automatic Speech Recognition
(ASR) transcriptions, enhancing the readability and quality of transcriptions. Without …
(ASR) transcriptions, enhancing the readability and quality of transcriptions. Without …
End-to-end speech to intent prediction to improve E-commerce customer support voicebot in Hindi and English
A Goyal, A Singh, N Garera - arXiv preprint arXiv:2211.07710, 2022 - arxiv.org
Automation of on-call customer support relies heavily on accurate and efficient speech-to-
intent (S2I) systems. Building such systems using multi-component pipelines can pose …
intent (S2I) systems. Building such systems using multi-component pipelines can pose …
Building robust spoken language understanding by cross attention between phoneme sequence and asr hypothesis
Building Spoken Language Understanding (SLU) robust to Automatic Speech Recognition
(ASR) errors is an essential issue for various voice-enabled virtual assistants. Considering …
(ASR) errors is an essential issue for various voice-enabled virtual assistants. Considering …
GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systems
A Robatian, M Hajipour, MR Peyghan, F Rajabi… - arXiv preprint arXiv …, 2025 - arxiv.org
Automatic Speech Recognition (ASR) systems have demonstrated remarkable performance
across various applications. However, limited data and the unique language features of …
across various applications. However, limited data and the unique language features of …
Recent Progress in Conversational AI
Z Xue, R Li, M Li - arXiv preprint arXiv:2204.09719, 2022 - arxiv.org
Conversational artificial intelligence (AI) is becoming an increasingly popular topic among
industry and academia. With the fast development of neural network-based models, a lot of …
industry and academia. With the fast development of neural network-based models, a lot of …
A Token-Wise Beam Search Algorithm for RNN-T
G Keren - 2023 IEEE Automatic Speech Recognition and …, 2023 - ieeexplore.ieee.org
Standard Recurrent Neural Network Transducers (RNN-T) decoding algorithms for speech
recognition are iterating over the time axis, such that one time step is decoded before …
recognition are iterating over the time axis, such that one time step is decoded before …
An ASR N-Best Transcript Neural Ranking Model for Spoken Content Retrieval
Spoken Content Retrieval (SCR) using ASR transcripts is in-creasingly important for
multimedia content archives. How-ever, SCR is often impacted by ASR errors. In recent …
multimedia content archives. How-ever, SCR is often impacted by ASR errors. In recent …