Abstract
Speech recognition applications are known to require a significant amount of resources. However, embedded speech recognition only authorizes few KB of memory, few MIPS, and small amount of training data. In order to fit the resource constraints of embedded applications, an approach based on a semicontinuous HMM system using state-independent acoustic modelling is proposed. A transformation is computed and applied to the global model in order to obtain each HMM state-dependent probability density functions, authorizing to store only the transformation parameters. This approach is evaluated on two tasks: digit and voice-command recognition. A fast adaptation technique of acoustic models is also proposed. In order to significantly reduce computational costs, the adaptation is performed only on the global model (using related speaker recognition adaptation techniques) with no need for state-dependent data. The whole approach results in a relative gain of more than 20% compared to a basic HMM-based system fitting the constraints.
Highlights
The amount and the diversity of services offered by the latest generation of mobile phones has increased significantly during the last decade, and these new services are considered as crucial points by the manufacturers in terms of both functionalities and marketing impact
With the compact model, we note a decrease of the Digit Error Rate (DER) from 4.32% to 2.17% which corresponds to a relative decrease of about 50%
DER is between 2.17% and 2.83%
Summary
The amount and the diversity of services offered by the latest generation of mobile phones (and similar embedded devices) has increased significantly during the last decade, and these new services are considered as crucial points by the manufacturers in terms of both functionalities and marketing impact. Most of the recent ASR systems rely on Gaussian or state sharing, where parameter tying reduces computational time and the memory footprint, whilst providing an efficient way of estimating large contextdependent models [4,5,6]. We present a new acoustic-model architecture where parameters are massively factored, with the purpose of reducing the memory footprint of an embedded ASR system whilst preserving the recognition accuracy. This factoring relies on a multi-level modelling scheme where a universal background model can be successively specialized to environment, speaker, and acoustic units.
Sign-in/Register to view highlights & summary 
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call