121 search results - page 1 / 25 » Corrected tandem features for acoustic model training |
ICASSP
2008
IEEE
13 years 11 months ago
2008
IEEE
This paper describes a simple method for significantly improving Tandem features used to train acoustic models for large-vocabulary speech recognition. The linear activations at ...
ICASSP
2009
IEEE
13 years 11 months ago
2009
IEEE
We measure the effects of a weak language model, estimated from as little as 100k words of text, on unsupervised acoustic model training and then explore the best method of using ...
INTERSPEECH
2010
12 years 12 months ago
2010
This paper presents a novel automatic speaker age and gender identification approach which combines five different methods at the acoustic level to improve the baseline performanc...
INTERSPEECH
2010
12 years 12 months ago
2010
This paper describes a new toolkit - SCARF - for doing speech recognition with segmental conditional random fields. It is designed to allow for the integration of numerous, possib...
ICASSP
2008
IEEE
13 years 11 months ago
2008
IEEE
With the purpose of improving Spoken Language Understanding (SLU) performance, a combination of different acoustic speech recognition (ASR) systems is proposed. State a-posteriori...