connectionist temporal classification

IMPROVING CTC-BASED SPEECH RECOGNITION VIA KNOWLEDGE TRANSFERRING FROM PRE-TRAINED LANGUAGE MODELS

NEURAL AUDIO-TO-SCORE MUSIC TRANSCRIPTION FOR UNCONSTRAINED POLYPHONY USING COMPACT OUTPUT REPRESENTATIONS

END-TO-END LOW RESOURCE KEYWORD SPOTTING THROUGH CHARACTER RECOGNITION AND BEAM-SEARCH RE-SCORING

HIERARCHICAL CONDITIONAL END-TO-END ASR WITH CTC AND MULTI-GRANULAR SUBWORD UNITS

DISENTANGLING CONTENT AND FINE-GRAINED PROSODY INFORMATION VIA HYBRID ASR BOTTLENECK FEATURES FOR VOICE CONVERSION