Jonathan Shen
YOU?
Author Swipe
View article: TRACE: A Time-Relational Approximate Cubing Engine for Fast Data Insights
TRACE: A Time-Relational Approximate Cubing Engine for Fast Data Insights Open
A large class of data questions can be modeled as identifying important slices of data driven by user defined metrics. This paper presents TRACE, a Time-Relational Approximate Cubing Engine that enables interactive analysis on such slices …
View article: Training Text-To-Speech Systems From Synthetic Data: A Practical Approach For Accent Transfer Tasks
Training Text-To-Speech Systems From Synthetic Data: A Practical Approach For Accent Transfer Tasks Open
Transfer tasks in text-to-speech (TTS) synthesis - where one or more aspects of the speech of one set of speakers is transferred to another set of speakers that do not feature these aspects originally - remains a challenging task. One of t…
View article: Examining Scaling and Transfer of Language Model Architectures for Machine Translation
Examining Scaling and Transfer of Language Model Architectures for Machine Translation Open
Natural language understanding and generation models follow one of the two dominant architectural paradigms: language models (LMs) that process concatenated sequences in a single stack of layers, and encoder-decoder models (EncDec) that ut…
View article: Sports at Play in American Politics
Sports at Play in American Politics Open
Sports have been a vital element to American entertainment for decades, which are only gaining popularity. Various sport events allow Americans to temporarily escape the stress associated with their social lives and the divisiveness of par…
View article: PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS
PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS Open
This paper introduces PnG BERT, a new encoder model for neural TTS. This model is augmented from the original BERT model, by taking both phoneme and grapheme representations of text as input, as well as the word-level alignment between the…
View article: Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling Open
This paper introduces Parallel Tacotron 2, a non-autoregressive neural text-to-speech model with a fully differentiable duration model which does not require supervised duration signals. The duration model is based on a novel attention mec…
View article: Parallel Tacotron: Non-Autoregressive and Controllable TTS
Parallel Tacotron: Non-Autoregressive and Controllable TTS Open
Although neural end-to-end text-to-speech models can synthesize highly natural speech, there is still room for improvements to its efficiency and naturalness. This paper proposes a non-autoregressive neural text-to-speech model augmented w…
View article: Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling
Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling Open
This paper presents Non-Attentive Tacotron based on the Tacotron 2 text-to-speech model, replacing the attention mechanism with an explicit duration predictor. This improves robustness significantly as measured by unaligned duration ratio …
View article: Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling Open
Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models. Lingvo models are composed of modular building blocks that are flexible an…
View article: Hierarchical Generative Modeling for Controllable Speech Synthesis
Hierarchical Generative Modeling for Controllable Speech Synthesis Open
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, background noise, and …
View article: Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis Open
We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently …
View article: Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions Open
This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spect…
View article: In Teacher We Trust: Learning Compressed Models for Pedestrian Detection
In Teacher We Trust: Learning Compressed Models for Pedestrian Detection Open
Deep convolutional neural networks continue to advance the state-of-the-art in many domains as they grow bigger and more complex. It has been observed that many of the parameters of a large network are redundant, allowing for the possibili…