44 citations · 79 across the 8 of their papers we have counts for
9 papers
Learning the joint distribution of two sequences using little or no paired data
Soroosh Mariooryad, Matt Shannon, Siyuan Ma +5
We present a noisy channel generative model of two sequences, for example text and speech, which enables uncovering the association between the two modalities when limited paired d…
Global Normalization for Streaming Speech Recognition in a Modular Framework
Ehsan Variani, Ke Wu, Michael Riley +3
We introduce the Globally Normalized Autoregressive Transducer (GNAT) for addressing the label bias problem in streaming speech recognition. Our solution admits a tractable exact c…
Speaker Generation
Daisy Stanton, Matt Shannon, Soroosh Mariooryad +4
This work explores the task of synthesizing speech in nonexistent human-sounding voices. We call this task "speaker generation", and present TacoSpawn, a system that performs compe…
Non-saturating GAN training as divergence minimization
Matt Shannon, Ben Poole, Soroosh Mariooryad +5
Non-saturating generative adversarial network (GAN) training is widely used and has continued to obtain groundbreaking results. However so far this approach has lacked strong theor…
Properties of f-divergences and f-GAN training
Matt Shannon
In this technical report we describe some properties of f-divergences and f-GAN training. We present an elementary derivation of the f-divergence lower bounds which form the basis…
Semi-Supervised Generative Modeling for Controllable Speech Synthesis
Raza Habib, Soroosh Mariooryad, Matt Shannon +5
We present a novel generative model that combines state-of-the-art neural text-to-speech (TTS) with semi-supervised probabilistic latent variable models. By providing partial super…
Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis
Eric Battenberg, RJ Skerry-Ryan, Soroosh Mariooryad +4
Despite the ability to produce human-level speech for in-domain text, attention-based end-to-end text-to-speech (TTS) systems suffer from text alignment failures that increase in f…
Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis
Eric Battenberg, Soroosh Mariooryad, Daisy Stanton +4
Recent work has explored sequence-to-sequence latent variable models for expressive speech synthesis (supporting control and transfer of prosody and style), but has not presented a…
Optimizing expected word error rate via sampling for speech recognition
Matt Shannon
State-level minimum Bayes risk (sMBR) training has become the de facto standard for sequence-level training of speech recognition acoustic models. It has an elegant formulation usi…