Speech processing Universal PERformance Benchmark (SUPERB) is a leaderboard to
benchmark the performance of Self-Supervised Learning (SSL) models on various speech …

Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech
Recognition (ASR) performance in low-resource settings. In this context, it has been …

The ability to dynamically adjust the computational load of neural models during inference is
crucial for on-device processing scenarios characterised by limited and time-varying …

The ability to dynamically adjust the computational load of neural models during inference is
crucial for on-device processing scenarios characterised by limited and time-varying …

This paper presents a speaker diarization model that incorporates label dependency via
intermediate predictions. The proposed method is categorized as an end-to-end neural …

This dissertation addresses speaker diarization, the task of partitioning a multi-talker audio
recording into speaker-wise segments. Speaker diarization has long been studied as a …

While the autoregressive transformer models of automatic speech recognition (ASR) are
highly accurate, the inference time is long because of their sequential decoding. Early exit is …