Source Themes

Can We ''Cherry-Pick''? Investigating Multiple Renditions from a Generative Speech Synthesis Model

In _ICASSP 2025_; Hyderabad, India

What do people hear? Listeners’ perception of conversational speech

In _Interspeech 2024_; Kos, Greece

PairwiseTurnGPT: a multi-stream turn prediction model for spoken dialogue

In _SemDial 2024_; Rovereto, Italy

Information Value: Measuring Utterance Predictability as Distance from Plausible Alternatives

In _EMNLP 2023_; Singapore

Quantifying the perceptual value of lexical and non-lexical channels in speech

In _Interspeech 2023_; Dublin, Ireland

Do dialogue representations align with perception? An empirical study

In _EACL 2023_; Dubrovnik, Croatia

Investigating perception of spoken dialogue acceptability through surprisal

In _Interspeech 2022_; Incheon, South Korea || **Awarded ISCA Best Student Paper**

Investigating perception of spoken dialogue acceptability through surprisal

Stimuli for Interspeech 2022

It's not what you said, it's how you said it: discriminative perception of speech as a multichannel communication system

In _Interspeech 2021_; Brno, Czech Republic

It's not what you said, it's how you said it: discriminative perception of speech as a multichannel communication system EVENT

In _Interspeech 2021_; Brno, Czech Republic