Search Results for author: Soroosh Mariooryad

Found 8 papers, 2 papers with code

Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM

no code implementations24 May 2023 Eliya Nachmani, Alon Levkovitch, Roy Hirsch, Julian Salazar, Chulayuth Asawaroengchai, Soroosh Mariooryad, Ehud Rivlin, RJ Skerry-Ryan, Michelle Tadmor Ramanovich

Key to our approach is a training objective that jointly supervises speech recognition, text continuation, and speech synthesis using only paired speech-text pairs, enabling a `cross-modal' chain-of-thought within a single decoding pass.

Language Modelling Question Answering +3

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

no code implementations6 Dec 2022 Soroosh Mariooryad, Matt Shannon, Siyuan Ma, Tom Bagby, David Kao, Daisy Stanton, Eric Battenberg, RJ Skerry-Ryan

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 data is available.

Variational Inference

Speaker Generation

no code implementations7 Nov 2021 Daisy Stanton, Matt Shannon, Soroosh Mariooryad, RJ Skerry-Ryan, Eric Battenberg, Tom Bagby, David Kao

We call this task "speaker generation", and present TacoSpawn, a system that performs competitively at this task.

Transfer Learning

Non-saturating GAN training as divergence minimization

no code implementations15 Oct 2020 Matt Shannon, Ben Poole, Soroosh Mariooryad, Tom Bagby, Eric Battenberg, David Kao, Daisy Stanton, RJ Skerry-Ryan

Non-saturating generative adversarial network (GAN) training is widely used and has continued to obtain groundbreaking results.

Generative Adversarial Network

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

3 code implementations23 Oct 2019 Eric Battenberg, RJ Skerry-Ryan, Soroosh Mariooryad, Daisy Stanton, David Kao, Matt Shannon, Tom Bagby

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 frequency for out-of-domain text.

Speech Synthesis

Semi-Supervised Generative Modeling for Controllable Speech Synthesis

no code implementations ICLR 2020 Raza Habib, Soroosh Mariooryad, Matt Shannon, Eric Battenberg, RJ Skerry-Ryan, Daisy Stanton, David Kao, Tom Bagby

We present a novel generative model that combines state-of-the-art neural text-to-speech (TTS) with semi-supervised probabilistic latent variable models.

Speech Synthesis

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

1 code implementation8 Jun 2019 Eric Battenberg, Soroosh Mariooryad, Daisy Stanton, RJ Skerry-Ryan, Matt Shannon, David Kao, Tom Bagby

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 coherent framework for understanding the trade-offs between the competing methods.

Expressive Speech Synthesis Style Transfer

Cannot find the paper you are looking for? You can Submit a new open access paper.