Exploration of End-to-End ASR for OpenSTT – Russian Open Speech-to-Text Dataset

06/15/2020
by   Andrei Andrusenko, et al.
0

This paper presents an exploration of end-to-end automatic speech recognition systems (ASR) for the largest open-source Russian language data set – OpenSTT. We evaluate different existing end-to-end approaches such as joint CTC/Attention, RNN-Transducer, and Transformer. All of them are compared with the strong hybrid ASR system based on LF-MMI TDNN-F acoustic model. For the three available validation sets (phone calls, YouTube, and books), our best end-to-end model achieves word error rate (WER) of 34.8 respectively. Under the same conditions, the hybridASR system demonstrates 33.5

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/07/2020

Homophone-based Label Smoothing in End-to-End Automatic Speech Recognition

A new label smoothing method that makes use of prior knowledge of a lang...
research
11/05/2021

Conformer-based Hybrid ASR System for Switchboard Dataset

The recently proposed conformer architecture has been successfully used ...
research
01/26/2021

Leveraging End-to-End ASR for Endangered Language Documentation: An Empirical Study on Yoloxóchitl Mixtec

"Transcription bottlenecks", created by a shortage of effective human tr...
research
12/03/2020

End to End ASR System with Automatic Punctuation Insertion

Recent Automatic Speech Recognition systems have been moving towards end...
research
08/08/2018

End-to-end Speech Recognition with Word-based RNN Language Models

This paper investigates the impact of word-based RNN language models (RN...
research
10/15/2020

Lightweight End-to-End Speech Recognition from Raw Audio Data Using Sinc-Convolutions

Many end-to-end Automatic Speech Recognition (ASR) systems still rely on...
research
08/08/2020

Word Error Rate Estimation Without ASR Output: e-WER2

Measuring the performance of automatic speech recognition (ASR) systems ...

Please sign up or login with your details

Forgot password? Click here to reset