arXiv subjects

Gaurav Bharaj

Publications and source records attributed to Gaurav Bharaj.

26 records · Page 2Linked to original sources

arXiv2021

Flavored Tacotron: Conditional Learning for Prosodic-linguistic Features

Neural sequence-to-sequence text-to-speech synthesis (TTS), such as Tacotron-2, transforms text into high-quality speech. However, generating speech with natural prosody still remains a challenge. Yasuda et. al. show that unlike natural speech, Tacotron-2's encoder doesn't fully represent prosodic features (e.g. syllable stress in English) from characters, and result in flat fundamental frequency variations. In this work, we propose a novel carefully designed strategy for conditioning Tacotron-2 on two fundamental prosodic features in English -- stress syllable and pitch accent, that help achieve more natural prosody. To this end, we use of a classifier to learn these features in an end-to-end fashion, and apply feature conditioning at three parts of Tacotron-2's Text-To-Mel Spectrogram: pre-encoder, post-encoder, and intra-decoder. Further, we show that jointly conditioned features at pre-encoder and intra-decoder stages result in prosodically natural synthesized speech (vs. Tacotron-2), and allows the model to produce speech with more accurate pitch accent and stress patterns. Quantitative evaluations show that our formulation achieves higher fundamental frequency contour correlation, and lower Mel Cepstral Distortion measure between synthesized and natural speech. And subjective evaluation shows that the proposed method's Mean Opinion Score of 4.14 fairs higher than baseline Tacotron-2, 3.91, when compared against natural speech (LJSpeech corpus), 4.28.

cs.SD↗

arXiv2021

Generative Landmarks

We propose a general purpose approach to detect landmarks with improved temporal consistency, and personalization. Most sparse landmark detection methods rely on laborious, manually labelled landmarks, where inconsistency in annotations over a temporal volume leads to sub-optimal landmark learning. Further, high-quality landmarks with personalization is often hard to achieve. We pose landmark detection as an image translation problem. We capture two sets of unpaired marked (with paint) and unmarked videos. We then use a generative adversarial network and cyclic consistency to predict deformations of landmark templates that simulate markers on unmarked images until these images are indistinguishable from ground-truth marked images. Our novel method does not rely on manually labelled priors, is temporally consistent, and image class agnostic -- face, and hand landmarks detection examples are shown.

cs.CV↗

arXiv2021

Grapheme-to-Phoneme Transformer Model for Transfer Learning Dialects

Grapheme-to-Phoneme (G2P) models convert words to their phonetic pronunciations. Classic G2P methods include rule-based systems and pronunciation dictionaries, while modern G2P systems incorporate learning, such as, LSTM and Transformer-based attention models. Usually, dictionary-based methods require significant manual effort to build, and have limited adaptivity on unseen words. And transformer-based models require significant training data, and do not generalize well, especially for dialects with limited data. We propose a novel use of transformer-based attention model that can adapt to unseen dialects of English language, while using a small dictionary. We show that our method has potential applications for accent transfer for text-to-speech, and for building robust G2P models for dialects with limited pronunciation dictionary size. We experiment with two English dialects: Indian and British. A model trained from scratch using 1000 words from British English dictionary, with 14211 words held out, leads to phoneme error rate (PER) of 26.877%, on a test set generated using the full dictionary. The same model pretrained on CMUDict American English dictionary, and fine-tuned on the same dataset leads to PER of 2.469% on the test set.

cs.CL↗

arXiv2021

Practical Face Reconstruction via Differentiable Ray Tracing

We present a differentiable ray-tracing based novel face reconstruction approach where scene attributes - 3D geometry, reflectance (diffuse, specular and roughness), pose, camera parameters, and scene illumination - are estimated from unconstrained monocular images. The proposed method models scene illumination via a novel, parameterized virtual light stage, which in-conjunction with differentiable ray-tracing, introduces a coarse-to-fine optimization formulation for face reconstruction. Our method can not only handle unconstrained illumination and self-shadows conditions, but also estimates diffuse and specular albedos. To estimate the face attributes consistently and with practical semantics, a two-stage optimization strategy systematically uses a subset of parametric attributes, where subsequent attribute estimations factor those previously estimated. For example, self-shadows estimated during the first stage, later prevent its baking into the personalized diffuse and specular albedos in the second stage. We show the efficacy of our approach in several real-world scenarios, where face attributes can be estimated even under extreme illumination conditions. Ablation studies, analyses and comparisons against several recent state-of-the-art methods show improved accuracy and versatility of our approach. With consistent face attributes reconstruction, our method leads to several style -- illumination, albedo, self-shadow -- edit and transfer applications, as discussed in the paper.

cs.CV↗

arXiv2020

StyleRig: Rigging StyleGAN for 3D Control over Portrait Images

StyleGAN generates photorealistic portrait images of faces with eyes, teeth, hair and context (neck, shoulders, background), but lacks a rig-like control over semantic face parameters that are interpretable in 3D, such as face pose, expressions, and scene illumination. Three-dimensional morphable face models (3DMMs) on the other hand offer control over the semantic parameters, but lack photorealism when rendered and only model the face interior, not other parts of a portrait image (hair, mouth interior, background). We present the first method to provide a face rig-like control over a pretrained and fixed StyleGAN via a 3DMM. A new rigging network, RigNet is trained between the 3DMM's semantic parameters and StyleGAN's input. The network is trained in a self-supervised manner, without the need for manual annotations. At test time, our method generates portrait images with the photorealism of StyleGAN and provides explicit control over the 3D semantic parameters of the face.

cs.CV↗

arXiv2019

Face Reflectance and Geometry Modeling via Differentiable Ray Tracing

We present a novel strategy to automatically reconstruct 3D faces from monocular images with explicitly disentangled facial geometry (pose, identity and expression), reflectance (diffuse and specular albedo), and self-shadows. The scene lights are modeled as a virtual light stage with pre-oriented area lights used in conjunction with differentiable Monte-Carlo ray tracing to optimize the scene and face parameters. With correctly disentangled self-shadows and specular reflection parameters, we can not only obtain robust facial geometry reconstruction, but also gain explicit control over these parameters, with several practical applications. We can change facial expressions with accurate resultant self-shadows or relight the scene and obtain accurate specular reflection and several other parameter combinations.

cs.CV↗

arXiv2019

FML: Face Model Learning from Videos

Monocular image-based 3D reconstruction of faces is a long-standing problem in computer vision. Since image data is a 2D projection of a 3D face, the resulting depth ambiguity makes the problem ill-posed. Most existing methods rely on data-driven priors that are built from limited 3D face scans. In contrast, we propose multi-frame video-based self-supervised training of a deep network that (i) learns a face identity model both in shape and appearance while (ii) jointly learning to reconstruct 3D faces. Our face model is learned using only corpora of in-the-wild video clips collected from the Internet. This virtually endless source of training data enables learning of a highly general 3D face model. In order to achieve this, we propose a novel multi-frame consistency loss that ensures consistent shape and appearance across multiple frames of a subject's face, thus minimizing depth ambiguity. At test time we can use an arbitrary number of frames, so that we can perform both monocular as well as multi-frame reconstruction.

cs.CV↗

arXiv2018

Metamorphs: Bistable Planar Structures

Extreme deformation can drastically morph a structure from one structural form into another. Programming such deformation properties into the structure is often challenging and in many cases an impossible task. The morphed forms do not hold and usually relapse to the original form, where the structure is in its lowest energy state. For example, a stick, when bent, resists its bent form and tends to go back to its initial straight form, where it holds the least amount of potential energy. In this project, we present a computational design method which can create fabricable planar structure that can morph into two different bistable forms. Once the user provides the initial desired forms, the method automatically creates support structures (internal springs), such that, the structure can not only morph, but also hold the respective forms under external force application. We achieve this through an iterative nonlinear optimization strategy for shaping the potential energy of the structure in the two forms simultaneously. Our approach guarantees first and second-order stability with respect to the potential energy of the bistable structure.

cs.GR↗