Hilbert frames theory have been extended to frames in Hilbert $C^*$-modules. The paper introduces equivalent $*$-frames and presents ordinary duals of a constructed $*$-frame by an adjointable and invertible operator. Also, some necessary and sufficient conditions are studied such that $*$-frames and ordinary duals or operator duals of another $*$-frames are equivalent under these conditions. W...

This paper proposes a lip reading technique for speech recognition by using motion estimation analysis. Motion estimation is done for lip movement image sequences representing speech. In this methodology, the motion estimation is computed without extracting the speaker’s lip contours and location. This leads to obtaining robust visual features for lip movements representing utterances. Our meth...

In this paper, we report our semantic tagging tool for spoken dialogue corpus. This tagging tool can acquire analysis rules using Transformation-based Learning (TBL) from small scale training corpus. It can learn dialogue act tagging rules and semantic frame tagging rules. The precisions are 72% in dialogue act tagging and 58% of semantic frame tagging in open test.

BACKGROUND AND PURPOSE Limb coordination is an element of motor control that is frequently disrupted following spinal cord injury (SCI). The authors assessed intralimb coordination in subjects with SCI following a 12-week program combining body weight support, electrical stimulation, and treadmill training. SUBJECTS Fourteen subjects with long-standing (mean time post-SCI=70 months, range=12-...

The proposal that the processing of visual time might rely on a network of distributed mechanisms that are vision-specific and timescale-specific stands in contrast to the classical view of time perception as the product of a single supramodal clock. Evidence showing that some of these mechanisms have a sensory component that can be locally adapted is at odds with another traditional assumption...

In recent studies, it has shown that speaker patterns can be learned from very short speech segments (e.g., 0.3 seconds) by a carefully designed convolutional & time-delay deep neural network (CT-DNN) model. By enforcing the model to discriminate the speakers in the training data, frame-level speaker features can be derived from the last hidden layer. In spite of its good performance, a potenti...

Pseudo orthogonal bases are a certain type of frames proposed in the engineering field, whose concept is equivalent to a tight frame with frame bound 1 in the frame terminology. This paper shows that pseudo orthogonal bases play an essential role in neural network learning. One of the most important issues in neural network learning is “what training data provides the optimal generalization cap...

In voice conversion, a simple frame-level mean and variance normalization is typically used for fundamental frequency (F0) transformation, which is text-independent and requires no parallel training data. Some advanced methods transform pitch contours instead, but require either parallel training data or syllabic annotations. We propose a method which retains the simplicity and text-independenc...