6 papers
FuseAlign: Forced Alignment in the Wild
Mithilesh Vaidya, Stephen Bailey, Sumukh Badam +2
Word-level forced alignment estimates when each transcript word occurs in an audio recording. It underpins text-based media editing, subtitling, speech-data curation, and phonetic…
Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation
Matthew Bendel, Stephen W. Bailey, Mithilesh Vaidya +2
Long-horizon video generation suffers from two intertwined issues. First, there is drift, where video quality degrades over time. Second, there are continuity issues which manifest…
PoDAR: Power-Decoupled Audio Representation for Generative Modeling
Alejandro Luebs, Mithilesh Vaidya, Ishaan Kumar +5
The performance of audio latent diffusion models is primarily governed by generator expressivity and the modelability of the underlying latent space. While recent research has focu…
Deep Learning for Assessment of Oral Reading Fluency
Mithilesh Vaidya, Binaya Kumar Sahoo, Preeti Rao
Reading fluency assessment is a critical component of literacy programmes, serving to guide and monitor early education interventions. Given the resource intensive nature of the ex…
Deep Learning For Prominence Detection In Children's Read Speech
Mithilesh Vaidya, Kamini Sabu, Preeti Rao
The detection of perceived prominence in speech has attracted approaches ranging from the design of linguistic knowledge-based acoustic features to the automatic feature learning f…
CNN Encoding of Acoustic Parameters for Prominence Detection
Kamini Sabu, Mithilesh Vaidya, Preeti Rao
Expressive reading, considered the defining attribute of oral reading fluency, comprises the prosodic realization of phrasing and prominence. In the context of evaluating oral read…