Contextualizing ASR with LLM using phonetic retrieval-based augmentation
Large language models (LLMs) have demonstrated excellent ability to model multimodal signals, including audio and text, allowing the model to ...
Tag: ASR
Apple researchers propose a new AI algorithm to optimize a byte-level representation for automatic speech recognition (ASR) and compare it to the UTF-8 representation
End-to-end (E2E) neural networks have emerged as flexible and accurate models for multilingual automatic speech recognition (ASR). However, as the ...
Optimizing byte-level representation for end-to-end ASR
This paper was accepted into the IEEE Spoken Language technology (SLT) 2024 Workshop. In this paper, we propose an algorithm ...
Hypernetworks to personalize ASR to atypical speech
*Equal taxpayers Parameter efficient fine-tuning (PEFT) for customizing automatic speech recognition (ASR) has recently shown promise for adapting general population ...
Corpus Synthesis for Zero-Shot ASR Domain Adaptation Using Large Language Models
While automatic speech recognition (ASR) systems are widely used in many real-world applications, they often do not generalize well to ...
Humanizing Word Error Rate for Readability and Accessibility of ASR Transcriptions
Podcasting has become a popular and powerful medium for storytelling, news and entertainment. Without transcriptions, podcasts may be inaccessible to ...
This Google AI article presents an innovative non-autoregressive ASR system fused with LM for superior multilingual speech recognition
The evolution of technology in speech recognition has been marked by significant advances, but challenges such as latency (the delay ...
Leveraging Large Language Models to Exploit ASR Uncertainty
With the help of creative engineering and learning in context, large language models (LLMs) are known to generalize well to ...
Importance of Optimizer-Induced Fluency in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR
In this article, we begin by training end-to-end automatic speech recognition (ASR) models using federated learning (FL) and examining the ...
Amazon Transcribe announces new ASR system based on voice-based model that expands support to more than 100 languages
Amazon Transcribe is a fully managed automatic speech recognition (ASR) service that makes it easy for you to add speech-to-text ...
Recommended.
