International Business Machines Corporation

Nuance Communications, Inc.

Radek Hampl

Pavel Krbec

Jan Sedivy

Jonathan Palgon

Daniel E Badt

John W Eckhart

Michael Florio

Tomas Beran

The present invention discloses a solution for conserving computing resources when implementing transformation based adaptation techniques. The disclosed solution limits the amount of speech data used by real-time adaptation algorithms to compute a transformation, which results in substantial computational savings. Appreciably, application of a transform is a relatively low memory and computationally cheap process compared to memory and resource requirements for computing the transform to be applied.

Resource conservative transformation based unsupervised speaker adaptation

The present invention discloses a method for semantically processing speech for speech recognition purposes. The method can reduce an amount of memory required for a Viterbi search of an N-gram language model having a value of N greater than two and also having at least one embedded grammar that appears in a multiple contexts to a memory size of approximately a bigram model search space with respect to the embedded grammar. The method also reduces needed CPU requirements. Achieved reductions can be accomplished by representing the embedded grammar as a recursive transition network (RTN), where only one instance of the recursive transition network is used for the contexts. Other than the embedded grammars, a Hidden Markov Model (HMM) strategy can be used for the search space.

Enhancement to Viterbi speech processing algorithm for hybrid speech models that conserves memory

Growing community of inventors

Praha, Czechia

Radek Hampl