pith. sign in

Librispeech: an asr corpus based on public domain audio books

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.CV 1

years

2025 2

representative citing papers

WhisperRT -- Turning Whisper into a Causal Streaming Model

cs.CL · 2025-08-17 · conditional · novelty 6.0

WhisperRT converts Whisper to a causal streaming ASR model via encoder causality, decoder synchronization on partial states, and fine-tuning, achieving better performance than non-fine-tuned streaming methods on sub-300ms chunks with lower complexity.

JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching

cs.CV · 2025-06-30 · unverdicted · novelty 6.0

JAM-Flow introduces a unified flow-matching model with a Multi-Modal Diffusion Transformer that jointly synthesizes facial motion and speech from text, audio, or motion inputs.

citing papers explorer

Showing 2 of 2 citing papers.

  • WhisperRT -- Turning Whisper into a Causal Streaming Model cs.CL · 2025-08-17 · conditional · none · ref 28

    WhisperRT converts Whisper to a causal streaming ASR model via encoder causality, decoder synchronization on partial states, and fine-tuning, achieving better performance than non-fine-tuned streaming methods on sub-300ms chunks with lower complexity.

  • JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching cs.CV · 2025-06-30 · unverdicted · none · ref 45

    JAM-Flow introduces a unified flow-matching model with a Multi-Modal Diffusion Transformer that jointly synthesizes facial motion and speech from text, audio, or motion inputs.