**Convolutional Hough Matching**, or **CHM**, is a geometric matching algorithm that distributes similarities of candidate matches over a geometric transformation space and evaluates them in a convolutional manner. It is casted into a trainable neural layer with a  semi-isotropic high-dimensional kernel, which learns non-rigid matching with a small number of interpretable parameters.

**DV3 Convolution Block** is a convolutional block used for the [Deep Voice 3](https://paperswithcode.com/method/deep-voice-3) text-to-speech architecture. It consists of a 1-D [convolution](https://paperswithcode.com/method/convolution) with a gated linear unit and a [residual connection](https://paperswithcode.com/method/residual-connection). In the Figure, $c$ denotes the dimensionality of the input. The convolution output of size $2 \cdot c$ is split into equal-sized portions: the gate vector and the input vector. A scaling factor $\sqrt{0.5}$ is used to ensure that we preserve the input variance early in training. The gated linear unit provides a linear path for the gradient flow, which alleviates the vanishing gradient issue for stacked convolution blocks while retaining non-linearity. To introduce speaker-dependent control, a speaker-dependent embedding is added as a bias to the convolution filter output, after a softsign function. The authors use the softsign nonlinearity because it limits the range of the output while also avoiding the saturation problem that exponential based nonlinearities sometimes exhibit. Convolution filter weights are initialized with zero-mean and unit-variance activations throughout the entire network.

DV3 Convolution Block

Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning

Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence

**Glow-TTS** is a flow-based generative model for parallel TTS that does not require any external aligner. By combining the properties of flows and dynamic programming, the proposed model searches for the most probable monotonic alignment between text and the latent representation of speech.  The model is directly trained to maximize the log-likelihood of speech with the alignment. Enforcing hard monotonic alignments helps enable robust TTS, which generalizes to long utterances, and employing flows enables fast, diverse, and controllable speech synthesis.

Source	Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com