Align With Purpose: Optimize Desired Properties In CTC Models With A General Plug-and-play Framework

Abstract

Connectionist Temporal Classification (CTC) is a widely used criterion for training supervised sequence-to-sequence (seq2seq) models. It enables learning the relations between input and output sequences, termed alignments, by marginalizing over perfect alignments (that yield the ground truth), at the expense of imperfect alignments. This binary differentiation of perfect and imperfect alignments falls short of capturing other essential alignment properties that hold significance in other real-world applications. Here we propose \(\textit\{Align With Purpose\}\), a \(\textbf\{general Plug-and-Play framework\}\) for enhancing a desired property in models trained with the CTC criterion. We do that by complementing the CTC with an additional loss term that prioritizes alignments according to a desired property. Our method does not require any intervention in the CTC loss function, enables easy optimization of a variety of properties, and allows differentiation between both perfect and impe

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysegev2023align

Related papers

• Variational Connectionist Temporal Classification For Order-preserving Sequence Modeling (2023)5.24
• Gram-ctc: Automatic Unit Selection And Target Decomposition For Sequence Labelling (2017)0.00
• Comparison Of Decoding Strategies For CTC Acoustic Models (2017)10.48
• Towards Personalization Of CTC Speech Recognition Models With Contextual Adapters And Adaptive Boosting (2022)0.00
• CR-CTC: Consistency Regularization On CTC For Improved Speech Recognition (2024)6.30
• A Study Of All-convolutional Encoders For Connectionist Temporal Classification (2017)5.84
• BERT Meets CTC: New Formulation Of End-to-end Speech Recognition With Pre-trained Masked Language Model (2022)0.00
• Efficient CTC Regularization Via Coarse Labels For End-to-end Speech Translation (2023)0.00