SLP-L13: Text-based customization for speech-to-text
Wed, 17 Apr, 13:10 - 15:10 (UTC +9)
Location: Room 102
Session Type: Lecture
Session Co-Chairs: Xie Chen, Shanghai Jiaotong University and Rohit Prabhavalkar, Google
Track: Speech and Language Processing
Click the to view the manuscript on IEEE Xplore Open Preview
Wed, 17 Apr, 13:10 - 13:30 (UTC +9)
SLP-L13.1: PERSONALIZATION OF CTC-BASED END-TO-END SPEECH RECOGNITION USING PRONUNCIATION-DRIVEN SUBWORD TOKENIZATION
Wed, 17 Apr, 13:30 - 13:50 (UTC +9)
SLP-L13.2: SEACO-PARAFORMER: A NON-AUTOREGRESSIVE ASR SYSTEM WITH FLEXIBLE AND EFFECTIVE HOTWORD CUSTOMIZATION ABILITY
Wed, 17 Apr, 13:50 - 14:10 (UTC +9)
SLP-L13.3: PHONEME-AWARE ENCODING FOR PREFIX-TREE-BASED CONTEXTUAL ASR
Wed, 17 Apr, 14:10 - 14:30 (UTC +9)
SLP-L13.4: CONTEXTUALIZED AUTOMATIC SPEECH RECOGNITION WITH ATTENTION-BASED BIAS PHRASE BOOSTED BEAM SEARCH
Wed, 17 Apr, 14:30 - 14:50 (UTC +9)
SLP-L13.5: SLIDESPEECH: A LARGE SCALE SLIDE-ENRICHED AUDIO-VISUAL CORPUS
Wed, 17 Apr, 14:50 - 15:10 (UTC +9)