English

ExKaldi-RT: A Real-Time Automatic Speech Recognition Extension Toolkit of Kaldi

Audio and Speech Processing 2021-08-10 v2 Computation and Language

Abstract

This paper describes the ExKaldi-RT online automatic speech recognition (ASR) toolkit that is implemented based on the Kaldi ASR toolkit and Python language. ExKaldi-RT provides tools for building online recognition pipelines. While similar tools are available built on Kaldi, a key feature of ExKaldi-RT that it works on Python, which has an easy-to-use interface that allows online ASR system developers to develop original research, such as by applying neural network-based signal processing and by decoding model trained with deep learning frameworks. We performed benchmark experiments on the minimum LibriSpeech corpus, and it showed that ExKaldi-RT could achieve competitive ASR performance in real-time recognition.

Cite

@article{arxiv.2104.01384,
  title  = {ExKaldi-RT: A Real-Time Automatic Speech Recognition Extension Toolkit of Kaldi},
  author = {Yu Wang and Chee Siang Leow and Akio Kobayashi and Takehito Utsuro and Hiromitsu Nishizaki},
  journal= {arXiv preprint arXiv:2104.01384},
  year   = {2021}
}

Comments

Accepted at the IEEE 10th Global Conference on Consumer Electronics

R2 v1 2026-06-24T00:49:28.670Z