Sentence examples for corresponding utterances from inspiring English sources

We collected the sentences and then recorded the corresponding utterances.

Our integrative recognition method uses a probability distribution which expresses the distribution of the time interval between the starting times of gestures and of the corresponding utterances.

As for gaps between corresponding utterances and gestures, we approximated the statistics using a Gaussian distribution with the same μ τ and σ τ 2 used in Eqn. (5) in Section 3. To allow for dynamic ranges of likelihood for speech, gestures, and time gaps between utterances and gestures, we set α, β, and γ in Equation 6 appropriately, as the result of a preliminary experiment.

Once we have obtained the normalized features, we classify the corresponding utterance with a multilayer perceptron (MLP) into two categories: angry and doubtful_or_bored.

This is possible in Aurora 2.0 because clean and noisy speech data are "parallel", i.e. each noisy utterance has a corresponding clean utterance.

The mouth movement of the talking head has to match the corresponding audio utterance.

where μ i is the constant corresponding to utterance X i and μ i can be estimated as μ i ≈ μ ij ¯ = 1 N ∑ j = 1 N μ ij.

In general, the stereo training data is used to train a mapping function from the distant-talking utterance to its corresponding close-talking utterance.

The DTW was used to align frames of a distant-talking utterance to frames of its corresponding close-talking utterance before they were used as the training data.

By aligning the corresponding words in utterances with gestures using dynamic programming (DP), we were able to reject pairs with low DP scores.

System P1B-STD is based on an exact match of the phone sequence output by a speech recognizer given the spoken query within the phone lattices corresponding to the utterances.