Subword and Crossword Units for CTC Acoustic Models

12/19/2017
by   Thomas Zenkel, et al.
0

This paper proposes a novel approach to create an unit set for CTC based speech recognition systems. By using Byte Pair Encoding we learn an unit set of an arbitrary size on a given training text. In contrast to using characters or words as units this allows us to find a good trade-off between the size of our unit set and the available training data. We evaluate both Crossword units, that may span multiple word, and Subword units. By combining this approach with decoding methods using a separate language model we are able to achieve state of the art results for grapheme based CTC systems.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/13/2018

Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units

In this paper, we present an end-to-end automatic speech recognition sys...
research
06/20/2016

A Nonparametric Bayesian Approach for Spoken Term detection by Example Query

State of the art speech recognition systems use data-intensive context-d...
research
11/08/2012

Multi-input Multi-output Beta Wavelet Network: Modeling of Acoustic Units for Speech Recognition

In this paper, we propose a novel architecture of wavelet network called...
research
05/08/2018

Comparing phonemes and visemes with DNN-based lipreading

There is debate if phoneme or viseme units are the most effective for a ...
research
11/20/2018

WEST: Word Encoded Sequence Transducers

Most of the parameters in large vocabulary models are used in embedding ...
research
10/21/2020

Improved inference for areal unit count data using graph-based optimisation

Spatial correlation in areal unit count data is typically modelled by a ...
research
08/04/2019

A Repairable System Supported by Two Spare Units and Serviced by Two Types of Repairers

We study a one-unit repairable system, supported by two identical spare ...

Please sign up or login with your details

Forgot password? Click here to reset