Submitted by Anonymous (not verified) on Wed, 02/21/2024 - 15:09
Abstract
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.
Submitted by Anonymous (not verified) on Wed, 02/21/2024 - 15:09
Abstract
Over the past three decades, the fields of automatic speech recognition (ASR) and machine translation (MT) have witnessed remarkable advancements, leading to exciting research directions such as speech-to-text translation (ST). This talk will delve into the domain of conversational ST, an essential facet of daily communication, which presents unique challenges including spontaneous informal language, the presence of disfluencies, high context dependence and a scarcity of ST paired data.
