Streaming Sequence Transduction through Dynamic Compression
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.
Code (1)
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSpeech-to-TextSimilar Papers 제목 키워드 기반
Text Summarization as Tree Transduction by Top-Down TreeLSTM
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 SummarizationStreaming Compression of Scientific Data via weak-SINDy
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 CompressionExact Hard Monotonic Attention for Character-Level Transduction
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 InflectionHPC: Hierarchical Point-based Latent Representation for Streaming Dynamic Gaussian Splatting Compression
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
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