Tom Bagby

CONTROLLABLE SPEECH SYNTHESIS

Eric Battenberg, R. Skerry-Ryan, Daisy Stanton, 2020 .

Speaker Generation pdf

Soroosh Mariooryad, Tom Bagby, Matt Shannon, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Learning the joint distribution of two sequences using little or no paired data

Siyuan Ma, Eric Battenberg, R. Skerry-Ryan, 2022, ArXiv.

Streaming End-to-end Speech Recognition for Mobile Devices

Tara N. Sainath, Ding Zhao, Ian McGraw, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Non-saturating GAN training as divergence minimization pdf

Soroosh Mariooryad, Tom Bagby, Matt Shannon, 2020, ArXiv.

Efficient Implementation of Recurrent Neural Network Transducer in Tensorflow

Khe Chai Sim, Tom Bagby, Kanishka Rao, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow

Tom Bagby, Michiel Bacchiani, Erik McDermott, 2017, INTERSPEECH.

Location-Relative Attention Mechanisms for Robust Long-Form Speech Synthesis

Eric Battenberg, R. Skerry-Ryan, Daisy Stanton, 2019, IEEE International Conference on Acoustics, Speech, and Signal Processing.

LAST: Scalable Lattice-Based Speech Modelling in JAX

M. Riley, Ehsan Variani, Tom Bagby, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Semi-Supervised Generative Modeling for Controllable Speech Synthesis pdf

Soroosh Mariooryad, Tom Bagby, Matt Shannon, 2019, ICLR.

Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis pdf

Soroosh Mariooryad, Tom Bagby, Matt Shannon, 2019, ArXiv.