Connectionist temporal classification
PulseAugur coverage of Connectionist temporal classification — every cluster mentioning Connectionist temporal classification across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New framework unifies Khmer text recognition and word segmentation
Researchers have developed a novel framework that jointly performs Khmer text recognition and word segmentation within a single model. This unified approach, utilizing a connectionist temporal classification decoder, ai…
-
New Transformer Encoder Tree architecture boosts multilingual translation efficiency
Researchers have developed a new architecture called Transformer Encoder Tree (TET) to improve multilingual machine translation and speech translation. This hierarchical, non-autoregressive model shares intermediate rep…
-
New CTC method improves diacritic restoration for Arabic speech transcripts
Researchers have developed an efficient, non-autoregressive method for diacritic restoration in Arabic speech transcripts using Connectionist Temporal Classification (CTC). This approach incorporates hard constraints du…
-
New Arabic Text Deduplication System Uses CTC for Improved LLM Efficiency
Researchers have developed CANDLE, a novel system for deduplicating characters in Arabic text, particularly addressing the challenge of distinguishing intentional character elongation from informal usage on social media…
-
New system CANDLE uses CTC for Arabic text noise deduplication
Researchers have developed CANDLE, a novel system for character-level Arabic noise deduplication. This system utilizes Connectionist Temporal Classification (CTC) to frame normalization as a sequence alignment problem, …