In speech recognition the data is typically a small amount of speech from the target speaker.
To infer the visitors' goal under the uncertainty intrinsic to these two modalities, we introduce Bayesian networks for combining noisy speech recognition with data from a laser scanner, which are independent of acoustic noise.
The service is designed to work over any landline telephone, meaning the company has had to find a way to do speech recognition using audio data sampled at a rate of 8kHz or 16kHz.
In fact, some recent proposals in the field of speech recognition and music data analysis use auditory models, thus exploiting the superiority of the human auditory system (e.g., [9 11]).
In speech recognition, whether unseen data will be from different or the same speakers as the training set influences the system, that is, whether the system needs to be speaker independent.
Although they have primarily been used in engineering applications such as automated speech recognition and seismic data processing, HMM techniques also appear to be very promising for predicting probabilities of individual customer behaviors from relatively short samples of recent product-purchasing histories.
To this end, the proposed approach is evaluated on three diverse ASR tasks: continuous phone recognition, connected digit recognition, and large vocabulary continuous speech recognition, but the data-driven knowledge module is trained with a single corpus and used in all three evaluation tasks without further training.
Automatic speech recognition experiments with noisy data demonstrate that subspace-based speech enhancement can significantly increase the robustness of these systems in additive coloured noise environments.
The company shifted to focus instead on speech recognition technology, using a data set of kids voices (which it did with parents' consent, we're told), to build Kidsense.
