Estimating Velum Height from Acoustics During Continuous Speech

K. Richmond

Estimating Velum Height from Acoustics During Continuous Speech

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

This paper reports on present work, in which a recurrent neural network is trained to estimate 'velum height' during continuous speech. Parallel acoustic-articulatory data comprising more than 400 read TIMIT sentences is obtained using electromagnetic articulography (EMA). This data is processed and used as training data for a range of neural network sizes. The network demonstrating the highest accuracy is identified. This performance is then evaluated in detail by analysing the network's output for each phonetic segment contained in 50 hand-labelled utterances set aside for testing purposes.

Original language	English
Title of host publication	Sixth European Conference on Speech Communication and Technology (EUROSPEECH'99)
Publisher	International Speech Communication Association
Pages	149-152
Number of pages	4
Publication status	Published - 1999

Access to Document

Richmond_1999_aAccepted author manuscript, 62.6 KB

http://www.isca-speech.org/archive/eurospeech_1999/e99_0149.html

Cite this

@inproceedings{e38e56561e2f4c528de044db73205f33,

title = "Estimating Velum Height from Acoustics During Continuous Speech",

abstract = "This paper reports on present work, in which a recurrent neural network is trained to estimate 'velum height' during continuous speech. Parallel acoustic-articulatory data comprising more than 400 read TIMIT sentences is obtained using electromagnetic articulography (EMA). This data is processed and used as training data for a range of neural network sizes. The network demonstrating the highest accuracy is identified. This performance is then evaluated in detail by analysing the network's output for each phonetic segment contained in 50 hand-labelled utterances set aside for testing purposes.",

author = "K. Richmond",

year = "1999",

language = "English",

pages = "149--152",

booktitle = "Sixth European Conference on Speech Communication and Technology (EUROSPEECH'99)",

publisher = "International Speech Communication Association",

}

TY - GEN

T1 - Estimating Velum Height from Acoustics During Continuous Speech

AU - Richmond, K.

PY - 1999

Y1 - 1999

N2 - This paper reports on present work, in which a recurrent neural network is trained to estimate 'velum height' during continuous speech. Parallel acoustic-articulatory data comprising more than 400 read TIMIT sentences is obtained using electromagnetic articulography (EMA). This data is processed and used as training data for a range of neural network sizes. The network demonstrating the highest accuracy is identified. This performance is then evaluated in detail by analysing the network's output for each phonetic segment contained in 50 hand-labelled utterances set aside for testing purposes.

AB - This paper reports on present work, in which a recurrent neural network is trained to estimate 'velum height' during continuous speech. Parallel acoustic-articulatory data comprising more than 400 read TIMIT sentences is obtained using electromagnetic articulography (EMA). This data is processed and used as training data for a range of neural network sizes. The network demonstrating the highest accuracy is identified. This performance is then evaluated in detail by analysing the network's output for each phonetic segment contained in 50 hand-labelled utterances set aside for testing purposes.

M3 - Conference contribution

SP - 149

EP - 152

BT - Sixth European Conference on Speech Communication and Technology (EUROSPEECH'99)

PB - International Speech Communication Association

ER -

Estimating Velum Height from Acoustics During Continuous Speech

Abstract / Description of output

Access to Document

Fingerprint

Cite this