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.

STAR 是一种基于 Transformer 的模型，用于在流数据上进行高效的序列转换。通过动态分割输入流创建压缩的锚点表示，STAR 在自动语音识别（ASR）中实现几乎无损压缩（12 倍），并优于现有方法。此外，在同时进行语音到文本任务中，STAR 展示出卓越的分割和延迟 - 质量权衡，优化延迟、内存占用和质量。

动态压缩中的流式序列转导

Streaming Sequence Transduction through Dynamic Compression

Sequence-to-sequence transduction is the core problem in language processing
applications as diverse as semantic parsing, machine translation, and
instruction following. The neural network models that provide the dominant
solution to these problems are brittle, especially in low-resource settings:
they fail to generalize correctly or systematically from small datasets. Past
work has shown that many failures of systematic generalization arise from
neural models' inability to disentangle lexical phenomena from syntactic ones.
To address this, we augment neural decoders with a lexical translation
mechanism that generalizes existing copy mechanisms to incorporate learned,
decontextualized, token-level translation rules. We describe how to initialize
this mechanism using a variety of lexicon learning algorithms, and show that it
improves systematic generalization on a diverse set of sequence modeling tasks
drawn from cognitive science, formal semantics, and machine translation.

通过引入词汇翻译机制并使用多种词典学习算法来初始化这种机制，可以提高序列建模任务的系统化泛化能力。