ICASSP 2022

PHONE-INFORMED REFINEMENT OF SYNTHESIZED MEL SPECTROGRAM FOR DATA AUGMENTATION IN SPEECH RECOGNITION

ATTRIBUTABLE WATERMARKING OF SPEECH GENERATIVE MODELS

ENHANCING AFFECTIVE REPRESENTATIONS OF MUSIC-INDUCED EEG THROUGH MULTIMODAL SUPERVISION AND LATENT DOMAIN ADAPTATION

A BENCHMARK OF STATE-OF-THE-ART SOUND EVENT DETECTION SYSTEMS EVALUATED ON SYNTHETIC SOUNDSCAPES

DISPEECH: A SYNTHETIC TOY DATASET FOR SPEECH DISENTANGLING

PATCH STEGANALYSIS: A SAMPLING BASED DEFENSE AGAINST ADVERSARIAL STEGANOGRAPHY

Threshold Independent Evaluation of Sound Event Detection Scores

BAYESIAN POPT-MODEL-SELECTION ESTIMATION

EMOTIONFLOW: CAPTURE THE DIALOGUE LEVEL EMOTION TRANSITIONS

MODELING OF PRE-TRAINED NEURAL NETWORK EMBEDDINGS LEARNED FROM RAW WAVEFORM FOR COVID-19 INFECTION DETECTION

IMPROVING END-TO-END CONTEXTUAL SPEECH RECOGNITION WITH FINE-GRAINED CONTEXTUAL KNOWLEDGE SELECTION

MULTI-TASK FMRI DATA FUSION USING IVA AND PARAFAC2