Progressive Alignment Objectives for Aligner-Encoder based ASR

2026-06-23 · Jaeyoung Lee, Masato Mimura, Takafumi Moriya arxiv

Aligner-Encoders are recently proposed seq2seq end-to-end ASR models that replace decoder attention by predicting the uth token directly from the u-th encoder position, so the encoder must learn the alignment internally without cross-attention or a transducer lattice. In practice, this alignment often forms abruptly in the upper layers, making training sensitive and brittle on long utterances. We propose InterAligner, which adds an intermediate Aligner objective so alignment can form progressively across depth, together with an intermediate CTC loss (InterCTC) to stabilize optimization. On LibriSpeech with a 17-layer Conformer, a final-only Aligner reaches 5.0/7.8 WER (test-clean/other). InterCTC improves to 3.4/6.0, and InterAligner further reduces WER to 3.1/5.6 with the largest gains on long utterances.

📄 PDF Abstract BibTeX arXiv:2606.24147

Code (0)

등록된 구현이 없습니다.

MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models

2024-03-25 · Kailai Yang, Zhiwei Liu, Qianqian Xie, Jimin Huang 외

Recent advancements in large language models (LLMs) focus on aligning to heterogeneous human expectations and values via multi-objective preference alignment. However, existing methods are dependent on the policy model p…

GPU In-Context Learning

Learning Noise-Resilient and Transferable Graph-Text Alignment via Dynamic Quality Assessment

2025-10-22 · Yuhang Liu, Minglai Shao, Zengyi Wo, Yunlong Chu 외 arxiv

Pre-training Graph Foundation Models (GFMs) on text-attributed graphs (TAGs) is central to web-scale applications such as search, recommendation, and knowledge discovery. However, existing CLIP-style graph-text aligners …

Representation Learning Cross-Modal Retrieval Node Classification Link Prediction

Word Alignment by Fine-tuning Embeddings on Parallel Corpora

2021-01-20 · EACL 2021 2 · Zi-Yi Dou, Graham Neubig

Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation o…

Cross-Lingual Transfer Translation Word Alignment Word Embeddings

SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment

2025-09-23 · Binod Singh, Sayan Deb Sarkar, Iro Armeni arxiv

Aligning 3D scene graphs is a crucial initial step for several applications in robot navigation and embodied perception. Current methods in 3D scene graph alignment often rely on single-modality point cloud data and stru…

3D Scene Graph Alignment Visual Localization Scene Understanding 3D Reconstruction

ClinicalAligner26AM: A Cross-Lingual Aligner for Dataset Translation; Evidences from the MultiClinCorpus Shared Task

2026-06-07 · François Remy arxiv

Word-level cross-lingual alignment is central to annotation projection, translation auditing, and cross-lingual faithfulness estimation, yet existing neural aligners are rarely adapted to specialized domains. In this pap…