Edinburgh Research Explorer

From HMMs to DNNs: Where Do the Improvements Come From?

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publication2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages5505-5509
Number of pages5
ISBN (Print)978-1-4799-9988-0
DOIs
Publication statusPublished - Mar 2016
Event41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - China, Shanghai, China
Duration: 20 Mar 201625 Mar 2016
https://www2.securecms.com/ICASSP2016/Default.asp

Conference

Conference41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
Abbreviated titleICASSP 2016
CountryChina
CityShanghai
Period20/03/1625/03/16
Internet address

Abstract

Deep neural networks (DNNs) have recently been the focus of much text-to-speech research as a replacement for decision trees and hidden Markov models (HMMs) in statistical parametric synthesis systems. Performance improvements have been reported; however, the configuration of systems evaluated makes it impossible to judge how much of the improvement is due to the new machine learning methods, and how much is due to other novel aspects of the systems. Specifically, whereas the decision trees in HMM-based systems typically operate at the state-level, and separate trees are used to handle separate acoustic streams, most DNN-based systems are trained to make predictions simultaneously for all streams at the level of the acoustic frame. This paper isolates the influence of three factors (machine learning method; state vs. frame predictions; separate vs. combined stream predictions) by building a continuum of systems along which only a single factor is varied at a time. We find that replacing decision trees with DNNs and moving from state-level to frame-level predictions both significantly improve listeners' naturalness ratings of synthetic speech produced by the systems. No improvement is found to result from switching from separate-stream to combined-stream predictions.

Download statistics

No data available

ID: 23618914