paper-with-me

Papers

Generative Modeling for Low Dimensional Speech Attributes with Neural Spline Flows

2022-03-03 · Kevin J. Shih, Rafael Valle, Rohan Badlani, João Felipe Santos, Bryan Catanzaro

Despite recent advances in generative modeling for text-to-speech synthesis, these models do not yet have the same fine-grained adjustability of pitch-conditioned deterministic models such as FastPitch and FastSpeech2. Pitch information is not only low-dimensional, but also discontinuous, making it particularly difficult to model in a generative setting. Our work explores several techniques for handling the aforementioned issues in the context of Normalizing Flow models. We also find this problem to be very well suited for Neural Spline flows, which is a highly expressive alternative to the more common affine-coupling mechanism in Normalizing Flows.

📄 PDF Abstract BibTeX arXiv:2203.01786

Code (1)

NVIDIA/radtts pytorch

Tasks

Speech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Hierarchical Generative Modeling for Controllable Speech Synthesis

2018-10-16 · ICLR 2019 5 · Wei-Ning Hsu, Yu Zhang, Ron J. Weiss, Heiga Zen 외

This paper proposes a neural sequence-to-sequence text-to-speech (TTS) model which can control latent attributes in the generated speech that are rarely annotated in the training data, such as speaking style, accent, bac…

AttributeSpeech Synthesistext-to-speechText to Speech

SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video

2024-12-13 · CVPR 2025 1 · Jongmin Park, Minh-Quan Viet Bui, Juan Luis Gonzalez Bello, Jaeho Moon 외

Synthesizing novel views from in-the-wild monocular videos is challenging due to scene dynamics and the lack of multi-view cues. To address this, we propose SplineGS, a COLMAP-free dynamic 3D Gaussian Splatting (3DGS) fr…

3DGSNovel View Synthesisparameter estimation

A Variational Framework for Improving Naturalness in Generative Spoken Language Models

2025-06-17 · Li-Wei Chen, Takuya Higuchi, Zakaria Aldeneh, Ahmed Hussen Abdelaziz 외

The success of large language models in text processing has inspired their adaptation to speech modeling. However, since speech is continuous and complex, it is often discretized for autoregressive modeling. Speech token…

Deep Random Splines for Point Process Intensity Estimation of Neural Population Data

2019-03-06 · NeurIPS 2019 12 · Gabriel Loaiza-Ganem, Sean M. Perkins, Karen E. Schroeder, Mark M. Churchland 외

Gaussian processes are the leading class of distributions on random functions, but they suffer from well known issues including difficulty scaling and inflexibility with respect to certain shape constraints (such as nonn…

Dimensionality ReductionGaussian ProcessesPoint Processes

A survey of probabilistic generative frameworks for molecular simulations

2024-11-14 · Richard John, Lukas Herron, Pratyush Tiwary

Generative artificial intelligence is now a widely used tool in molecular science. Despite the popularity of probabilistic generative models, numerical experiments benchmarking their performance on molecular data are lac…

BenchmarkingDenoisingModel SelectionSurvey