Soroosh Mariooryad

32 papers A* 2A 3B 3Misc 5Journal 18Unranked 1
YearRankTypeTitle / Venue / Authors
2025 — conf
Robust and Unbounded Length Generalization in Autoregressive Transformer-Based Text-to-Speech.
NAACL (Long Papers)
Eric Battenberg, R. J. Skerry-Ryan, Daisy Stanton, Soroosh Mariooryad, Matt Shannon, Julian Salazar, David Kao
2025 J jnl
SequenceLayers: Sequence Processing and Streaming Neural Networks Made Easy.
CoRR
R. J. Skerry-Ryan, Julian Salazar, Soroosh Mariooryad, David Kao, Daisy Stanton, Eric Battenberg, Matt Shannon, Ron J. Weiss, Robin Scheibler, Jonas Rothfuss, Tom Bagby
2025 A conf
Zero-Shot Mono-to-Binaural Speech Synthesis.
INTERSPEECH
Alon Levkovitch, Julian Salazar, Soroosh Mariooryad, R. J. Skerry-Ryan, Nadav Bar, W. Bastiaan Kleijn, Eliya Nachmani
2024 A* conf
Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM.
ICLR
Eliya Nachmani, Alon Levkovitch, Roy Hirsch, Julian Salazar, Chulayuth Asawaroengchai, Soroosh Mariooryad, Ehud Rivlin, R. J. Skerry-Ryan, Michelle Tadmor Ramanovich
2024 J jnl
Very Attentive Tacotron: Robust and Unbounded Length Generalization in Autoregressive Transformer-Based Text-to-Speech.
CoRR
Eric Battenberg, R. J. Skerry-Ryan, Daisy Stanton, Soroosh Mariooryad, Matt Shannon, Julian Salazar, David Kao
2024 J jnl
Zero-Shot Mono-to-Binaural Speech Synthesis.
CoRR
Alon Levkovitch, Julian Salazar, Soroosh Mariooryad, R. J. Skerry-Ryan, Nadav Bar, W. Bastiaan Kleijn, Eliya Nachmani
2023 J jnl
LMs with a Voice: Spoken Language Modeling beyond Speech Tokens.
CoRR
Eliya Nachmani, Alon Levkovitch, Julian Salazar, Chulayuth Asawaroengchai, Soroosh Mariooryad, R. J. Skerry-Ryan, Michelle Tadmor Ramanovich
2022 J jnl
Learning the joint distribution of two sequences using little or no paired data.
CoRR
Soroosh Mariooryad, Matt Shannon, Siyuan Ma, Tom Bagby, David Kao, Daisy Stanton, Eric Battenberg, R. J. Skerry-Ryan
2022 Misc conf
Speaker Generation.
ICASSP
Daisy Stanton, Matt Shannon, Soroosh Mariooryad, R. J. Skerry-Ryan, Eric Battenberg, Tom Bagby, David Kao
2021 J jnl
Speaker Generation.
CoRR
Daisy Stanton, Matt Shannon, Soroosh Mariooryad, R. J. Skerry-Ryan, Eric Battenberg, Tom Bagby, David Kao
2021 Misc conf
Wave-Tacotron: Spectrogram-Free End-to-End Text-to-Speech Synthesis.
ICASSP
Ron J. Weiss, R. J. Skerry-Ryan, Eric Battenberg, Soroosh Mariooryad, Diederik P. Kingma
2020 Misc conf
Location-Relative Attention Mechanisms for Robust Long-Form Speech Synthesis.
ICASSP
Eric Battenberg, R. J. Skerry-Ryan, Soroosh Mariooryad, Daisy Stanton, David Kao, Matt Shannon, Tom Bagby
2020 J jnl
Non-saturating GAN training as divergence minimization.
CoRR
Matt Shannon, Ben Poole, Soroosh Mariooryad, Tom Bagby, Eric Battenberg, David Kao, Daisy Stanton, R. J. Skerry-Ryan
2020 A* conf
Semi-Supervised Generative Modeling for Controllable Speech Synthesis.
ICLR
Raza Habib, Soroosh Mariooryad, Matt Shannon, Eric Battenberg, R. J. Skerry-Ryan, Daisy Stanton, David Kao, Tom Bagby
2020 J jnl
Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis.
CoRR
Ron J. Weiss, R. J. Skerry-Ryan, Eric Battenberg, Soroosh Mariooryad, Diederik P. Kingma
2019 J jnl
Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis.
CoRR
Eric Battenberg, Soroosh Mariooryad, Daisy Stanton, R. J. Skerry-Ryan, Matt Shannon, David Kao, Tom Bagby
2019 J jnl
Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis.
CoRR
Eric Battenberg, R. J. Skerry-Ryan, Soroosh Mariooryad, Daisy Stanton, David Kao, Matt Shannon, Tom Bagby
2019 J jnl
Semi-Supervised Generative Modeling for Controllable Speech Synthesis.
CoRR
Raza Habib, Soroosh Mariooryad, Matt Shannon, Eric Battenberg, R. J. Skerry-Ryan, Daisy Stanton, David Kao, Tom Bagby
2017 J jnl
The Cost of Dichotomizing Continuous Labels for Binary Classification Problems: Deriving a Bayesian-Optimal Classifier.
IEEE Trans. Affect. Comput.
Soroosh Mariooryad, Carlos Busso
2016 J jnl
Facial Expression Recognition in the Presence of Speech Using Blind Lexical Compensation.
IEEE Trans. Affect. Comput.
Soroosh Mariooryad, Carlos Busso
2015 J jnl
Correcting Time-Continuous Emotional Labels by Modeling the Reaction Lag of Evaluators.
IEEE Trans. Affect. Comput.
Soroosh Mariooryad, Carlos Busso
2014 Misc conf
Automatic characterization of speaking styles in educational videos.
ICASSP
Soroosh Mariooryad, Anitha Kannan, Dilek Hakkani-Tür, Elizabeth Shriberg
2014 A conf
Building a naturalistic emotional speech corpus by retrieving expressive behaviors from existing speech corpora.
INTERSPEECH
Soroosh Mariooryad, Reza Lotfian, Carlos Busso
2014 J jnl
Compensating for speaker or lexical variabilities in speech for emotion recognition.
Speech Commun.
Soroosh Mariooryad, Carlos Busso
2013 B conf
Analysis and Compensation of the Reaction Lag of Evaluators in Continuous Emotional Annotations.
ACII
Soroosh Mariooryad, Carlos Busso
2013 Misc conf
Audiovisual corpus to analyze whisper speech.
ICASSP
Tam Tran, Soroosh Mariooryad, Carlos Busso
2013 J jnl
Exploring Cross-Modality Affective Reactions for Audiovisual Emotion Recognition.
IEEE Trans. Affect. Comput.
Soroosh Mariooryad, Carlos Busso
2013 B conf
Feature and model level compensation of lexical content for facial emotion recognition.
FG
Soroosh Mariooryad, Carlos Busso
2013 J jnl
Iterative Feature Normalization Scheme for Automatic Emotion Detection from Speech.
IEEE Trans. Affect. Comput.
Carlos Busso, Soroosh Mariooryad, Angeliki Metallinou, Shrikanth S. Narayanan
2012 B conf
Factorizing speaker, lexical and emotional variabilities observed in facial expressions.
ICIP
Soroosh Mariooryad, Carlos Busso
2012 J jnl
Generating Human-Like Behaviors Using Joint, Speech-Driven Models for Conversational Agents.
IEEE Trans. Speech Audio Process.
Soroosh Mariooryad, Carlos Busso
2011 A conf
Detecting Sleepiness by Fusing Classifiers Trained with Novel Acoustic Features.
INTERSPEECH
Tauhidur Rahman, Soroosh Mariooryad, Shalini Keshavamurthy, Gang Liu, John H. L. Hansen, Carlos Busso