paper-with-me

Papers

Streaming Sequence Transduction through Dynamic Compression

2024-02-02 · Weiting Tan, Yunmo Chen, Tongfei Chen, Guanghui Qin, Haoran Xu, Heidi C. Zhang, Benjamin Van Durme, Philipp Koehn

We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dynamically segments input streams to create compressed anchor representations, achieving nearly lossless compression (12x) in Automatic Speech Recognition (ASR) and outperforming existing methods. Moreover, STAR demonstrates superior segmentation and latency-quality trade-offs in simultaneous speech-to-text tasks, optimizing latency, memory footprint, and quality.

📄 PDF Abstract BibTeX arXiv:2402.01172

Code (1)

steventan0110/star 공식 구현 pytorch

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSpeech-to-Text

Similar Papers 제목 키워드 기반

Text Summarization as Tree Transduction by Top-Down TreeLSTM

2018-09-24 · Davide Bacciu, Antonio Bruno

Extractive compression is a challenging natural language processing problem. This work contributes by formulating neural extractive compression as a parse tree transduction problem, rather than a sequence transduction ta…

SentenceSentence CompressionText Summarization

Streaming Compression of Scientific Data via weak-SINDy

2023-08-29 · Benjamin P. Russo, M. Paul Laiu, Richard Archibald

In this paper a streaming weak-SINDy algorithm is developed specifically for compressing streaming scientific data. The production of scientific data, either via simulation or experiments, is undergoing an stage of expon…

Data Compression

Exact Hard Monotonic Attention for Character-Level Transduction

2019-05-15 · ACL 2019 7 · Shijie Wu, Ryan Cotterell

Many common character-level, string-to string transduction tasks, e.g., grapheme-tophoneme conversion and morphological inflection, consist almost exclusively of monotonic transductions. However, neural sequence-to seque…

Hard AttentionInductive BiasMorphological Inflection

HPC: Hierarchical Point-based Latent Representation for Streaming Dynamic Gaussian Splatting Compression

2026-01-31 · Yangzhi Ma, Bojun Liu, Wenting Liao, Dong Liu 외 arxiv

While dynamic Gaussian Splatting has driven significant advances in free-viewpoint video, maintaining its rendering quality with a small memory footprint for efficient streaming transmission still presents an ongoing cha…

Sentence Compression as Tree Transduction

2014-01-15 · Trevor Anthony Cohn, Mirella Lapata

This paper presents a tree-to-tree transduction method for sentence compression. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus nat…

Local DistortionSentenceSentence Compression