Lip Forcing distills a 14B bidirectional video diffusion teacher into autoregressive students that achieve real-time lip synchronization at 31 FPS using two denoising steps without CFG.
hub
URL http://proceedings.mlr.press/ v37/allamanis15.html
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
other 1
citation-polarity summary
roles
other 1polarities
unclear 1representative citing papers
Moshi is the first real-time full-duplex spoken large language model that casts dialogue as speech-to-speech generation using parallel audio streams and an inner monologue of time-aligned text tokens.
Voxtral Realtime is an end-to-end trained streaming ASR model that achieves Whisper-level transcription quality at 480ms delay after scaling pretraining across 13 languages.
Step-Audio 2 integrates a latent audio encoder, reasoning-centric reinforcement learning, and discrete audio token generation into language modeling to deliver state-of-the-art performance on audio understanding and conversational benchmarks.
Atlas reaches over 42% accuracy on Natural Questions with only 64 examples, outperforming a 540B-parameter model by 3% with 50x fewer parameters.
Contrastive learning trains unsupervised dense retrievers that beat BM25 on most BEIR datasets and support cross-lingual retrieval across scripts.
Codex achieves 28.8% pass@1 on HumanEval, rising to 70.2% with 100 samples per problem via repeated sampling.
wav2VOT shows wav2vec2 can estimate voice onset time and related stop consonant features with accuracy comparable to existing tools on unseen data and higher accuracy after fine-tuning.
CoughPhase-CLR uses cough physiological phases to build contrastive positive pairs, outperforming random cropping on downstream tasks including COVID-19 detection and COPD classification.
F3-Tokenizer adapts audio autoencoder latents with noise-regularized bottleneck (channel normalization and stochastic perturbation) and a representation encoder (RQ-MTP plus frozen-LLM supervision) to support both high-dimensional understanding representations and normalized continuous generation ta
CAFNet performs joint ternary classification and temporal boundary regression for half-truth audio deepfakes via cross-attentive fusion of MFCC, LFCC, and Chroma-STFT features, reporting 92.71% accuracy and 0.075s MAE on MLADDC T2+T3.
A hybrid confidence-aware ASR training framework with learnable weights reduces Telugu medical WER from 24.3% to 15.8% and Kannada from 31.7% to 25.4%, outperforming standard fine-tuning.
Machine interpreting should shift from fidelity metrics to three design priorities—agency, grounding, and experience—drawn from interpreting studies to close the usability gap with human-mediated communication.
Domain-adapted ECG foundation models with self-supervised pretraining and selective fine-tuning reach macro-AUROC 0.8509 for multi-label structural heart disease detection on the EchoNext benchmark.
A survey of spatial speech perception systems covering sound source localization, directional enhancement, and automatic speech recognition methods and their integration.
Empirical comparison of LSTM, GNN, and Transformer architectures for NBA trajectory forecasting finds hybrid LSTM with contextual information yields lowest FDE of 1.51m over horizons up to 2s.
citing papers explorer
-
Voxtral Realtime
Voxtral Realtime is an end-to-end trained streaming ASR model that achieves Whisper-level transcription quality at 480ms delay after scaling pretraining across 13 languages.
-
Step-Audio 2 Technical Report
Step-Audio 2 integrates a latent audio encoder, reasoning-centric reinforcement learning, and discrete audio token generation into language modeling to deliver state-of-the-art performance on audio understanding and conversational benchmarks.
-
Atlas: Few-shot Learning with Retrieval Augmented Language Models
Atlas reaches over 42% accuracy on Natural Questions with only 64 examples, outperforming a 540B-parameter model by 3% with 50x fewer parameters.
-
Unsupervised Dense Information Retrieval with Contrastive Learning
Contrastive learning trains unsupervised dense retrievers that beat BM25 on most BEIR datasets and support cross-lingual retrieval across scripts.
-
wav2VOT: Automatic estimation of voice onset time, closure duration, and burst realisation with wav2vec2
wav2VOT shows wav2vec2 can estimate voice onset time and related stop consonant features with accuracy comparable to existing tools on unseen data and higher accuracy after fine-tuning.
-
CoughPhase-CLR: Designing an acoustics-informed foundation model for coughing sound classification
CoughPhase-CLR uses cough physiological phases to build contrastive positive pairs, outperforming random cropping on downstream tasks including COVID-19 detection and COPD classification.
-
F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation
F3-Tokenizer adapts audio autoencoder latents with noise-regularized bottleneck (channel normalization and stochastic perturbation) and a representation encoder (RQ-MTP plus frozen-LLM supervision) to support both high-dimensional understanding representations and normalized continuous generation ta
-
Audio Deepfake Detection with Half-Truth Localisation Using Cross-Attentive Feature Fusion
CAFNet performs joint ternary classification and temporal boundary regression for half-truth audio deepfakes via cross-attentive fusion of MFCC, LFCC, and Chroma-STFT features, reporting 92.71% accuracy and 0.075s MAE on MLADDC T2+T3.
-
Enhancing ASR Performance in the Medical Domain for Dravidian Languages
A hybrid confidence-aware ASR training framework with learnable weights reduces Telugu medical WER from 24.3% to 15.8% and Kannada from 31.7% to 25.4%, outperforming standard fine-tuning.
-
Bridging the Usability Gap: Lessons from Interpreting Studies for Machine Interpreting Design
Machine interpreting should shift from fidelity metrics to three design priorities—agency, grounding, and experience—drawn from interpreting studies to close the usability gap with human-mediated communication.
-
Domain-Adapted Fine-Tuning of ECG Foundation Models for Multi-Label Structural Heart Disease Screening
Domain-adapted ECG foundation models with self-supervised pretraining and selective fine-tuning reach macro-AUROC 0.8509 for multi-label structural heart disease detection on the EchoNext benchmark.
-
Spatial Speech Perception Systems: A Survey of Sound Source Localization, Directional Enhancement, and Speech Recognition
A survey of spatial speech perception systems covering sound source localization, directional enhancement, and automatic speech recognition methods and their integration.
-
Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers
Empirical comparison of LSTM, GNN, and Transformer architectures for NBA trajectory forecasting finds hybrid LSTM with contextual information yields lowest FDE of 1.51m over horizons up to 2s.