Streamatt: Direct Streaming Speech-to-text Translation With Attention-based Audio History Selection

Abstract

Streaming speech-to-text translation (StreamST) is the task of automatically translating speech while incrementally receiving an audio stream. Unlike simultaneous ST (SimulST), which deals with pre-segmented speech, StreamST faces the challenges of handling continuous and unbounded audio streams. This requires additional decisions about what to retain of the previous history, which is impractical to keep entirely due to latency and computational constraints. Despite the real-world demand for real-time ST, research on streaming translation remains limited, with existing works solely focusing on SimulST. To fill this gap, we introduce StreamAtt, the first StreamST policy, and propose StreamLAAL, the first StreamST latency metric designed to be comparable with existing metrics for SimulST. Extensive experiments across all 8 languages of MuST-C v1.0 show the effectiveness of StreamAtt compared to a naive streaming baseline and the related state-of-the-art SimulST policy, providing a first

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keypapi2024streamatt

Related papers

• Streamspeech: Simultaneous Speech-to-speech Translation With Multi-task Learning (2024)7.81
• Alignatt: Using Attention-based Audio-translation Alignments As A Guide For Simultaneous Speech Translation (2023)3.58
• Direct Simultaneous Speech-to-text Translation Assisted By Synchronized Streaming ASR (2021)6.77
• Efficient And Adaptive Simultaneous Speech Translation With Fully Unidirectional Architecture (2025)2.26
• Large-scale Streaming End-to-end Speech Translation With Neural Transducers (2022)9.59
• Diarist: Streaming Speech Translation With Speaker Diarization (2023)0.00
• Learning When To Translate For Streaming Speech (2021)9.23
• Synchronous Speech Recognition And Speech-to-text Translation With Interactive Decoding (2019)10.48