papers

Publications (13)

cs.CL2019

Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis

Ye Jia, Yu Zhang, Ron J. Weiss +8

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 d…

cs.CL2021

PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS

Ye Jia, Heiga Zen, Jonathan Shen +2

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 tex…

cs.SD2021

Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling

Isaac Elias, Heiga Zen, Jonathan Shen +4

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 si…

cs.CL2018

Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions

Jonathan Shen, Ruoming Pang, Ron J. Weiss +10

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 predictio…

cs.SD2020

Parallel Tacotron: Non-Autoregressive and Controllable TTS

Isaac Elias, Heiga Zen, Jonathan Shen +4

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…

cs.AI2018

Neural Program Synthesis with Priority Queue Training

Daniel A. Abolafia, Mohammad Norouzi, Jonathan Shen +2

We consider the task of program synthesis in the presence of a reward function over the output of programs, where the goal is to find programs with maximal rewards. We employ an it…

cs.CV2016

In Teacher We Trust: Learning Compressed Models for Pedestrian Detection

Jonathan Shen, Noranart Vesdapunt, Vishnu N. Boddeti +1

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 o…

cs.LG2019

Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

Jonathan Shen, Patrick Nguyen, Yonghui Wu +88

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 a…

cs.CL2018

Hierarchical Generative Modeling for Controllable Speech Synthesis

Wei-Ning Hsu, Yu Zhang, Ron J. Weiss +9

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 d…

cs.CL2022

Examining Scaling and Transfer of Language Model Architectures for Machine Translation

Biao Zhang, Behrooz Ghorbani, Ankur Bapna +4

Natural language understanding and generation models follow one of the two dominant architectural paradigms: language models (LMs) that process concatenated sequences in a single s…

cs.SD2021

Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling

Jonathan Shen, Ye Jia, Mike Chrzanowski +4

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 robust…

cs.IR2024

TRACE: A Time-Relational Approximate Cubing Engine for Fast Data Insights

Suharsh Sivakumar, Jonathan Shen, Rajat Monga

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 Cubi…

cs.SD2022

Training Text-To-Speech Systems From Synthetic Data: A Practical Approach For Accent Transfer Tasks

Lev Finkelstein, Heiga Zen, Norman Casagrande +9

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 thes…