UMID infers membership in contrastive pre-training data using only text queries by performing latent inversion and comparing similarity and variability signals to synthetic gibberish references via unsupervised anomaly detection.
Librispeech: An asr corpus based on public domain audio books
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 5roles
dataset 1polarities
use dataset 1representative citing papers
On synthetic banking speech alone, GRPO cuts ASR WER 40% relative to SFT (36.71%→22.09%) by improving stopping calibration and attention anchoring to audio.
TTT-PLC adapts existing PLC models at test time via self-supervised synthetic masking of received audio packets, improving concealment on the same lossy signal in both file and streaming settings.
JASTIN is an instruction-driven audio evaluation system that achieves state-of-the-art correlation with human ratings on speech, sound, music, and out-of-domain tasks without task-specific retraining.
PhiNet adds phonetic interpretability to speaker verification while matching the accuracy of standard black-box models on VoxCeleb, SITW, and LibriSpeech.
citing papers explorer
-
Membership Inference for Contrastive Pre-training Models with Text-only PII Queries
UMID infers membership in contrastive pre-training data using only text queries by performing latent inversion and comparing similarity and variability signals to synthetic gibberish references via unsupervised anomaly detection.
-
When Synthetic Speech Is All You Have: Better Call GRPO
On synthetic banking speech alone, GRPO cuts ASR WER 40% relative to SFT (36.71%→22.09%) by improving stopping calibration and attention anchoring to audio.
-
Self-Supervised Test-Time Tuning for Packet Loss Concealment
TTT-PLC adapts existing PLC models at test time via self-supervised synthetic masking of received audio packets, improving concealment on the same lossy signal in both file and streaming settings.
-
JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions
JASTIN is an instruction-driven audio evaluation system that achieves state-of-the-art correlation with human ratings on speech, sound, music, and out-of-domain tasks without task-specific retraining.
-
PhiNet: Speaker Verification with Phonetic Interpretability
PhiNet adds phonetic interpretability to speaker verification while matching the accuracy of standard black-box models on VoxCeleb, SITW, and LibriSpeech.