Search Results

A Parallelizable Lattice Rescoring Strategy with Neural Language Models

kaldi-asr/kaldi 8 Mar 2021

This paper proposes a parallel computation strategy and a posterior-based lattice expansion algorithm for efficient lattice rescoring with neural language models (LMs) for automatic speech recognition.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Wake Word Detection with Alignment-Free Lattice-Free MMI

kaldi-asr/kaldi 17 May 2020

Always-on spoken language interfaces, e. g. personal digital assistants, rely on a wake word to start processing spoken input.

The SpeakIn System for VoxCeleb Speaker Recognition Challange 2021

kaldi-asr/kaldi 5 Sep 2021

The minDCF of our submission is 0. 1034, and the corresponding EER is 1. 8460%.

Sound Audio and Speech Processing

Cannot find the paper you are looking for? You can Submit a new open access paper.