Search Results - "Kastner, Kyle"

Deep learning-based point-scanning super-resolution imaging by Fang, Linjing, Monroe, Fred, Novak, Sammy Weiser, Kirk, Lyndsey, Schiavon, Cara R., Yu, Seungyoon B., Zhang, Tong, Wu, Melissa, Kastner, Kyle, Latif, Alaa Abdel, Lin, Zijun, Shaw, Andrew, Kubota, Yoshiyuki, Mendenhall, John, Zhang, Zhao, Pekkurnaz, Gulcin, Harris, Kristen, Howard, Jeremy, Manor, Uri

“…Point-scanning imaging systems are among the most widely used tools for high-resolution cellular and tissue imaging, benefiting from arbitrarily defined pixel…”
Get full text

Representation Mixing for TTS Synthesis by Kastner, Kyle, Santos, Joao Felipe, Bengio, Yoshua, Courville, Aaron

“…Recent character and phoneme-based parametric TTS systems using deep learning have shown strong performance in natural speech generation. However, the choice…”
Get full text

Understanding Shared Speech-Text Representations by Wang, Gary, Kastner, Kyle, Bapna, Ankur, Chen, Zhehuai, Rosenberg, Andrew, Ramabhadran, Bhuvana, Zhang, Yu

“…Recently, a number of approaches to train speech models by incorporating text into end-to-end models have been developed, with Maestro advancing…”
Get full text

Deep Learning‐Based Point‐Scanning Super‐Resolution Imaging by Manor, Uri, Fang, Linjing, Howard, Jeremy, Monroe, Fred, Weiser, Sammy, Kastner, Kyle, Kirk, Lyndsey, Harris, Kristen, Pekkurnaz, Gulcin, Yoon, Blenda, Schiavon, Cara, Zhang, Tong

“…Abstract only…”
Get full text

Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data by Saeki, Takaaki, Wang, Gary, Morioka, Nobuyuki, Elias, Isaac, Kastner, Kyle, Rosenberg, Andrew, Ramabhadran, Bhuvana, Zen, Heiga, Beaufays, Francoise, Shemtov, Hadar

“…Collecting high-quality studio recordings of audio is challenging, which limits the language coverage of text-to-speech (TTS) systems. This paper proposes a…”
Get full text

ReSeg: A Recurrent Neural Network-Based Model for Semantic Segmentation by Visin, Francesco, Romero, Adriana, Kyunghyun Cho, Matteucci, Matteo, Ciccone, Marco, Kastner, Kyle, Bengio, Yoshua, Courville, Aaron

“…We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of…”
Get full text

R-MelNet: Reduced Mel-Spectral Modeling for Neural TTS by Kastner, Kyle, Courville, Aaron

“…This paper introduces R-MelNet, a two-part autoregressive architecture with a frontend based on the first tier of MelNet and a backend WaveRNN-style audio…”
Get full text

Zero-shot Cross-lingual Voice Transfer for TTS by Biadsy, Fadi, Chen, Youzheng, Elias, Isaac, Kastner, Kyle, Wang, Gary, Rosenberg, Andrew, Ramabhadran, Bhuvana

“…In this paper, we introduce a zero-shot Voice Transfer (VT) module that can be seamlessly integrated into a multi-lingual Text-to-speech (TTS) system to…”
Get full text

Understanding Shared Speech-Text Representations by Wang, Gary, Kastner, Kyle, Bapna, Ankur, Chen, Zhehuai, Rosenberg, Andrew, Ramabhadran, Bhuvana, Zhang, Yu

“…Recently, a number of approaches to train speech models by incorpo-rating text into end-to-end models have been developed, with Mae-stro advancing…”
Get full text

Adversarial training of Keyword Spotting to Minimize TTS Data Overfitting by Park, Hyun Jin, Agarwal, Dhruuv, Chen, Neng, Sun, Rentao, Partridge, Kurt, Chen, Justin, Zhang, Harry, Zhu, Pai, Bartel, Jacob, Kastner, Kyle, Wang, Gary, Rosenberg, Andrew, Wang, Quan

“…The keyword spotting (KWS) problem requires large amounts of real speech training data to achieve high accuracy across diverse populations. Utilizing large…”
Get full text

Utilizing TTS Synthesized Data for Efficient Development of Keyword Spotting Model by Park, Hyun Jin, Agarwal, Dhruuv, Chen, Neng, Sun, Rentao, Partridge, Kurt, Chen, Justin, Zhang, Harry, Zhu, Pai, Bartel, Jacob, Kastner, Kyle, Wang, Gary, Rosenberg, Andrew, Wang, Quan

“…This paper explores the use of TTS synthesized training data for KWS (keyword spotting) task while minimizing development cost and time. Keyword spotting…”
Get full text

Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data by Saeki, Takaaki, Wang, Gary, Morioka, Nobuyuki, Elias, Isaac, Kastner, Kyle, Biadsy, Fadi, Rosenberg, Andrew, Ramabhadran, Bhuvana, Zen, Heiga, Beaufays, Françoise, Shemtov, Hadar

“…Collecting high-quality studio recordings of audio is challenging, which limits the language coverage of text-to-speech (TTS) systems. This paper proposes a…”
Get full text

High-precision Voice Search Query Correction via Retrievable Speech-text Embedings by Li, Christopher, Wang, Gary, Kastner, Kyle, Su, Heng, Chen, Allen, Rosenberg, Andrew, Chen, Zhehuai, Wu, Zelin, Velikovich, Leonid, Rondon, Pat, Caseiro, Diamantino, Aleksic, Petar

“…Automatic speech recognition (ASR) systems can suffer from poor recall for various reasons, such as noisy audio, lack of sufficient training data, etc…”
Get full text

MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling by Wu, Yusong, Manilow, Ethan, Deng, Yi, Swavely, Rigel, Kastner, Kyle, Cooijmans, Tim, Courville, Aaron, Huang, Cheng-Zhi Anna, Engel, Jesse

“…Musical expression requires control of both what notes are played, and how they are performed. Conventional audio synthesizers provide detailed expressive…”
Get full text

Planning in Dynamic Environments with Conditional Autoregressive Models by Hansen, Johanna, Kastner, Kyle, Courville, Aaron, Dudek, Gregory

“…We demonstrate the use of conditional autoregressive generative models (van den Oord et al., 2016a) over a discrete latent space (van den Oord et al., 2017b)…”
Get full text

Harmonic Recomposition using Conditional Autoregressive Modeling by Kastner, Kyle, Kumar, Rithesh, Cooijmans, Tim, Courville, Aaron

“…We demonstrate a conditional autoregressive pipeline for efficient music recomposition, based on methods presented in van den Oord et al.(2017). Recomposition…”
Get full text

Representation Mixing for TTS Synthesis by Kastner, Kyle, Santos, João Felipe, Bengio, Yoshua, Courville, Aaron

“…Recent character and phoneme-based parametric TTS systems using deep learning have shown strong performance in natural speech generation. However, the choice…”
Get full text

Blindfold Baselines for Embodied QA by Anand, Ankesh, Belilovsky, Eugene, Kastner, Kyle, Larochelle, Hugo, Courville, Aaron

“…We explore blindfold (question-only) baselines for Embodied Question Answering. The EmbodiedQA task requires an agent to answer a question by intelligently…”
Get full text

Learning Distributed Representations from Reviews for Collaborative Filtering by Almahairi, Amjad, Kastner, Kyle, Cho, Kyunghyun, Courville, Aaron

“…Recent work has shown that collaborative filter-based recommender systems can be improved by incorporating side information, such as natural language reviews,…”
Get full text

Learning to Discover Sparse Graphical Models by Belilovsky, Eugene, Kastner, Kyle, Varoquaux, Gaël, Blaschko, Matthew

“…We consider structure discovery of undirected graphical models from observational data. Inferring likely structures from few examples is a complex task often…”
Get full text