paper-with-me

Papers

A Differentiable Alignment Framework for Sequence-to-Sequence Modeling via Optimal Transport

2025-02-03 · Yacouba Kaloga, Shashi Kumar, Petr Motlicek, Ina Kodrasi

Accurate sequence-to-sequence (seq2seq) alignment is critical for applications like medical speech analysis and language learning tools relying on automatic speech recognition (ASR). State-of-the-art end-to-end (E2E) ASR systems, such as the Connectionist Temporal Classification (CTC) and transducer-based models, suffer from peaky behavior and alignment inaccuracies. In this paper, we propose a novel differentiable alignment framework based on one-dimensional optimal transport, enabling the model to learn a single alignment and perform ASR in an E2E manner. We introduce a pseudo-metric, called Sequence Optimal Transport Distance (SOTD), over the sequence space and discuss its theoretical properties. Based on the SOTD, we propose Optimal Temporal Transport Classification (OTTC) loss for ASR and contrast its behavior with CTC. Experimental results on the TIMIT, AMI, and LibriSpeech datasets show that our method considerably improves alignment performance, though with a trade-off in ASR performance when compared to CTC. We believe this work opens new avenues for seq2seq alignment research, providing a solid foundation for further exploration and development within the community.

📄 PDF Abstract BibTeX arXiv:2502.01588

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Similar Papers 제목 키워드 기반

Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction

2025-06-10 · Ruben Weitzman, Peter Mørch Groth, Lood Van Niekerk, Aoi Otani 외

Retrieving homologous protein sequences is essential for a broad range of protein modeling tasks such as fitness prediction, protein design, structure modeling, and protein-protein interactions. Traditional workflows hav…

Protein DesignRetrieval

D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation

2019-01-09 · CVPR 2019 6 · Chien-Yi Chang, De-An Huang, Yanan Sui, Li Fei-Fei 외

We address weakly supervised action alignment and segmentation in videos, where only the order of occurring actions is available during training. We propose Discriminative Differentiable Dynamic Time Warping (D3TW), the …

Dynamic Time WarpingSegmentationWeakly Supervised Action Segmentation (Transcript)

Differentiable Combinatorial Losses through Generalized Gradients of Linear Programs

2019-10-18 · Xi Gao, Han Zhang, Aliakbar Panahi, Tom Arodz

When samples have internal structure, we often see a mismatch between the objective optimized during training and the model's goal during inference. For example, in sequence-to-sequence modeling we are interested in high…

Combinatorial OptimizationDecoderGraph Matchingimage-classification+1

Self-Supervised Contrastive Learning for Videos using Differentiable Local Alignment

2024-09-06 · Keyne Oei, Amr Gomaa, Anna Maria Feit, João Belo

Robust frame-wise embeddings are essential to perform video analysis and understanding tasks. We present a self-supervised method for representation learning based on aligning temporal video sequences. Our framework uses…

Action RecognitionContrastive LearningRepresentation LearningVideo Alignment

Structured Reordering for Modeling Latent Alignments in Sequence Transduction

2021-06-06 · NeurIPS 2021 12 · Bailin Wang, Mirella Lapata, Ivan Titov

Despite success in many domains, neural models struggle in settings where train and test examples are drawn from different distributions. In particular, in contrast to humans, conventional sequence-to-sequence (seq2seq) …

Machine TranslationSemantic ParsingSystematic GeneralizationTranslation