MULTI-DOMAIN KNOWLEDGE DISTILLATION VIA UNCERTAINTY-MATCHING FOR END-TO-END ASR MODELS

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:INTERSPEECH (22. : 2021 : Brünn; Online) 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH 2021) ; Volume 2 of 6
1. Verfasser: Kim, Ho-Gyeong (VerfasserIn)
Weitere Verfasser: Lee, Min-Joong (VerfasserIn), Lee, Hoshik (VerfasserIn), Kang, Tae Gyoon (VerfasserIn), Lee, Jihyun (VerfasserIn), Yang, Eunho (VerfasserIn), Hwang, Sung Ju (VerfasserIn)
Pages:22
Format: UnknownFormat
Sprache:eng
Veröffentlicht: 2021
Schlagworte:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Titel Jahr Verfasser
IMPACT OF EMOTIONAL STATE ON ESTIMAT TION OF WILLINGNESS TO BUY FROM ADVERTISING SPEECH 2021 Nagano, Mizuki
ACOUSTIC ECHO CANCELLATION WITH CROSS-DOMAIN LEARNING 2021 Pfeifenberger, Lukas
Y2-NET FCRN FOR ACOUSTIC ECHO AND NOISE SUPPRESSION 2021 Seidel, Ernst
A SIMULTANEOUS DENOISING AND DEREVERBERATION FRAMEWORK WITH TARGET DECOUPLING 2021 Li, Andong
DEEP NOISE SUPPRESSION WITH NON-INTRUSIVE PESQNET SUPERVISION ENABLING THE USE OF REAL TRAINING DATA 2021 Xu, Zivi
TOWARD GENRE ADAPTED CLOSED CAPTIONING 2021 Buet, Francois
SPOKEN TERM DETECTION AND RELEVANCE SCORE ESTIMATION USING DOT- PRODUCT OF PRONUNCIA TION EMBEDDINGS 2021 Svec, Jan
IMPROVING ACCENT IDENTIFICATION AND ACCENTED SPEECH RECOGNITION UNDER A FRAMEWORK OF SELF-SUPERVISED LEARNING 2021 Deng, Keqi
CONTEXTUAL DENSITY RATIO FOR LANGUAGE MODEL BIASING OF SEQUENCE TO SEQUENCE ASR SYSTEMS 2021 Andres-Ferrer, Jesus
PHONETICALLY INDUCED SUBWORDS FOR END-TO-END SPEECH RECOGNITION 2021 Papadourakis, Vasileios
TOKEN-LEVEL SUPERVISED CONTRASTIVE LEARNING FOR PUNCTUATION RESTORATION 2021 Huang, Qiushi
BERT-BASED SEMANTIC MODEL FOR RESCORING N-BEST SPEECH RECOGNITION LIST 2021 Fohr, Dominique
BART BASED SEMANTIC CORRECTION FOR MANDARIN AUTOMATIC SPEECH RECOGNITION SYSTEM 2021 Zhao, Yun
TEXT AUGMENTATION FOR LANGUAGE MODELS IN HIGH ERROR RECOGNITION SCENARIO 2021 Benes, Karel
TRAINING HYBRID MODELS ON NOISY TRANSLITERATED TRANSCRIPTS FOR CODE-SWITCHED SPEECH RECOGNITION 2021 Wiesner, Matthew
AVLNET: LEARNING AUDIO-VISUAL LANGUAGE REPRESENTATIONS FROM INSTRUCTIONAL VIDEOS 2021 Rouditchenko, Andrew
THE ZERO RESOURCE SPEECH CHALLENGE 2021: SPOKEN LANGUAGE MODELLING 2021 Dunbar, Ewan
TOWARDS UNSUPERVISED PHONE AND WORD SEGMENTATION USING SELF- SUPERVISED VECTOR-QUANTIZED NEURAL NETWORKS 2021 Kamper, Herman
ZERO-SHOT FEDERATED LEARNING WITH NEW CLASSES FOR AUDIO CLASSIFICATION 2021 Gudur, Gautham Krishna
SPEECH REPRESENTATION LEARNING COMBINING CONFORMER CPC WITH DEEP CLUSTER FOR THE ZEROSPEECH CHALLENGE 2021 2021 Maekaku, Takashi
Alle Artikel auflisten