TRANSFORMER-BASED ASR INCORPORATING TIME-REDUCTION LAYER AND FINE- TUNING WITH SELF-KNOWLEDGE DISTILLATION

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: Haidar, Md. Akmal (VerfasserIn)
Weitere Verfasser: Xing, Chao (VerfasserIn), Rezagholizadeh, Mehdi (VerfasserIn)
Pages:22
Format: UnknownFormat
Sprache:eng
Veröffentlicht: 2021
Schlagworte:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Titel Jahr Verfasser
NON-VERBAL VOCALISATION AND LAUGHTER DETECTION USING SEQUENCE-TO- SEQUENCE MODELS AND MULTI-LABEL TRAINING 2021 Condron, Scott
AUTOMATIC SPEECH RECOGNITION SYSTEMS ERRORS FOR OBJECTIVE SLEEPINESS DETECTION THROUGH VOICE 2021 Martin, Vincent P.
INTERSPEECH 2021 DEEP NOISE SUPPRESSION CHALLENGE 2021 Reddy, Chandan K. A.
DBNET: A DUAL-BRANCH NETWORK ARCHITECTURE PROCESSING ON SPECTRUM AND WAVEFORM FOR SINGLE-CHANNEL SPEECH ENHANCEMENT 2021 Zhang, Kanghao
LIGHTWEIGHT CAUSAL TRANSFORMER WITH LOCAL SELF-ATTENTION FOR REAL-TIME SPEECH ENHANCEMENT 2021 Oostermeijer, Koen
DPCRN: DUAL-PATH CONVOLUTION RECURRENT NETWORK FOR SINGLE CHANNEL SPEECH ENHANCEMENT 2021 Le, Xiaohuai
SEMANTIC SENTENCE SIMILARITY: SIZE DOES NOT ALWAYS MATTER 2021 Merkx, Danny
E2E-BASED MULTI-TASK LEARNING APPROACH TO JOINT SPEECH AND ACCENT RECOGNITION 2021 Zhang, Jicheng
MODELING AND TRAINING STRATEGIES FOR LANGUAGE RECOGNITION SYSTEMS 2021 Duroselle, Raphael
REVISITING PARITY OF HUMAN VS. MACHINE CONVERSATIONAL SPEECH TRANSCRIPTION 2021 Mansfield, Courtney
CLASS-BASED NEURAL NETWORK LANGUAGE MODEL FOR SECOND-PASS RESCORING IN ASR 2021 Dai, Lingfeng
INCORPORATING EXTERNAL POS TAGGER FOR PUNCTUATION RESTORATION 2021 Shi, Ning
LOOKUP-TABLE RECURRENT LANGUAGE MODELS FOR LONG TAIL SPEECH RECOGNITION 2021 Huang, W. Ronny
A LIGHT-WEIGHT CONTEXTUAL SPELLING CORRECTION MODEL FOR CUSTOMIZING TRANSDUCER-BASED SPEECH RECOGNITION SYSTEMS 2021 Wang, Xiaoqiang
OUT-OF-VOCABULARY WORDS DETECTION WITH ATTENTION AND CTC ALIGNMENTS IN AN END-TO-END ASR SYSTEM 2021 Egorova, Ekaterina
ACOUSTIC DATA-DRIVEN SUBWORD MODELING FOR END-TO-END SPEECH RECOGNITION 2021 Zhou, Wei
ANALYZING SPEAKER INFORMATION IN SELF-SUPERVISED MODELS TO IMPROVE ZERO-RESOURCE SPEECH PROCESSING 2021 Niekerk, Benjamin Van
MULTILINGUAL TRANSFER OF ACOUSTIC WORD EMBEDDINGS IMPROVES WHEN TRAINING ON LANGUAGES RELATED TO THE TARGET ZERO-RESOURCE LANGUAGE 2021 Jacobs, Christiaan
UNSUPERVISED ACOUSTIC UNIT DISCOVERY BY LEVERAGING A LANGUVUAGE- INDEPENDENT SUBWORD DISCRIMINATIVE FEATURE REPRESENTATION 2021 Feng, Siyuan
IDENTIFYING INDICATORS OF VULNERABILITY FROM SHORT SPEECH SEGMENTS USING ACOUSTIC AND TEXTUAL FEATURES 2021 Cui, Xia
Alle Artikel auflisten