We propose a novel strategy ES3 for self-supervised learning of robust audio-visual speech
representations from unlabeled talking face videos. While many recent approaches for this …

Despite rapid advancement in recent years, current speech enhancement models often
produce speech that differs in perceptual quality from real clean speech. We propose a …

In recent years, the quality of text-to-speech (TTS) synthesis vastly improved due to deep-
learning techniques, with parallel architectures, in particular, providing excellent synthesis …

GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and
tones, marks a milestone for omni-modal foundation models. However, empowering Large …

A phonetic posteriorgram (PPG) is a time-varying categorical distribution over acoustic units
of speech (eg, phonemes). PPGs are a popular representation in speech generation due to …

Purpose: Oral diadochokinesis is a useful task in assessment of speech motor function in the
context of neurological disease. Remote collection of speech tasks provides a convenient …

We propose a system for modifying spoken notifications in a manner that is sensitive to the
music a user is listening to. Spoken notifications provide convenient access to rich …

Silent speech recognition is a promising technology that decodes human speech without
requiring audio signals, enabling private human-computer interactions. In this paper, we …

Phonetic forced alignment can greatly expedite spoken language analysis by providing
automatictimealignmentsattheword-andphone-levels. Inthecaseoflow-resourcelanguages, it …

In this project, we demonstrate that phoneme-based models for speech processing can
achieve strong crosslinguistic generalizability to unseen languages. We curated the …