New speech recognition model: Hidden Conditional Neural Fields

Sep 25, 2013
Model architectures of HMM, HCFR and HCNF.

Toyohashi Tech researchers propose the Hidden Conditional Neural Fields (HCNF) model for continuous speech recognition. The model is a combination of the Hidden Conditional Random Fields (HCRF) and a Multi-Layer Perceptron (MLP), that is, an extension of Hidden Markov Model (HMM).

This new model has the discriminative property for sequences from HCRF and the ability to extract non-linear features from an MLP. Furthermore, the HCNF can incorporate many types of features from non-linear features can be extracted, and is trained by sequential criteria.

In this paper, the researchers describe the formulation of HCNF and examine three methods to further improve using HCNF, which was an objective function that explicitly considered training errors, provided a hierarchical tandem-style feature, and included a deep non-linear feature extractor for the observation function.

HCRF can use a deep feed forward (DNN) in the observation function, and therefore, a sophisticated pre-training algorithm such as the deep belief network (DBN) can be used to provide a deep observation function.

The research shows that HCNF can be trained realistically without any initial model and outperform the HCRF and triphone hidden Markov model trained by the minimum phone error (MPE) manner using for continuous English phoneme recognition on the TIMIT core test and Japanese phoneme recognition on the IPA 100 test set.

Explore further: Computer scientists can predict the price of Bitcoin

More information: Fujii, Y., Yamamoto, K. and Nakagawa, S. Hidden Conditional Fields for Continuous Phoneme Speech Recognition, IEICE Trans. Inf.&Sys., E95-D,2094-2104 (2012). DOI: 10.1587/transinf.E95.D.2094

add to favorites email to friend print save as pdf

Related Stories

Speech recognition leaps forward

Aug 29, 2011

During Interspeech 2011, the 12th annual Conference of the International Speech Communication Association being held in Florence, Italy, from Aug. 28 to 31, researchers from Microsoft Research will present work that dramatically ...

Research aims to improve speech recognition software

Aug 11, 2010

Anyone who has used an automated airline reservation system has experienced the promise - and the frustration - inherent in today's automatic speech recognition technology. When it works, the computer "understands" that you ...

Bionic speech recognition

Sep 09, 2010

As speech recognition systems become more commonplace - on the computer desktop top, at the call centre and even in the car - it is increasingly important to ensure that the voice signal is as clear as possible before it ...

Smart listeners and smooth talkers

Nov 17, 2011

Human-like performance in speech technology could be just around the corner, thanks to a new research project that links three UK universities.

Recommended for you

Tablets, cars drive AT&T wireless gains—not phones

7 hours ago

AT&T says it gained 2 million wireless subscribers in the latest quarter, but most were from non-phone services such as tablets and Internet-connected cars. The company is facing pricing pressure from smaller rivals T-Mobile ...

Twitter looks to weave into more mobile apps

8 hours ago

Twitter on Wednesday set out to weave itself into mobile applications with a free "Fabric" platform to help developers build better programs and make more money.

Blink, point, solve an equation: Introducing PhotoMath

9 hours ago

"Ma, can I go now? My phone did my homework." PhotoMath, from the software development company MicroBlink, will make the student's phone do math homework. Just point the camera towards the mathematical expression, ...

Google unveils app for managing Gmail inboxes

9 hours ago

Google is introducing an application designed to make it easier for its Gmail users to find and manage important information that can often become buried in their inboxes.

User comments : 0