COSINE-DISTANCE VIRTUAL ADVERSARIAL TRAINING FOR SEMI-SUPERVISED SPEAKER-DISCRIMINATIVE ACOUSTIC EMBEDDINGS

von Kreyssig, Florian L.
Veröffentlicht in INTERSPEECH (21. : 2020 : Online) Cognitive intelligence for speech processing ; Volume 5 of 7 (2020)

VARIABLE FRAME RATE ACOUSTIC MODELS USING MINIMUM ERROR REINFORCEMENT LEARNING

von Jiang, Dongcheng
Veröffentlicht in INTERSPEECH (22. : 2021 : Brünn; Online) 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH 2021) ; Volume 2 of 6 (2021)

RESIDUAL ENERGY-BASED MODELS FOR END-TO-END SPEECH RECOGNITION

von Li, Oiujia
Veröffentlicht in INTERSPEECH (22. : 2021 : Brünn; Online) 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH 2021) ; Volume 3 of 6 (2021)