2025/02/01 by Anna Min, Chenxu Hu, Min, Anna +5 · 2 voices · 2 citations
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Multimedia (cs.MM) #Natural Language Processing Techniques #Sound (cs.SD) #cs.AI #cs.CL #cs.MM #cs.SD #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2502.00377
openalex publication_date 2025/02/01 · arxiv published 2025/02/01 · arxiv updated 2025/02/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Though end-to-end speech-to-text translation has been a great success, we argue that the cascaded speech-to-text translation model still has its place, which is usually criticized for the error propagation between automatic speech recognition (ASR) and machine translation (MT) models. In this paper, we explore the benefits of incorporating multiple candidates from ASR and self-supervised speech features into MT. Our analysis reveals that the primary cause of cascading errors stems from the increased divergence between similar samples in the speech domain when mapped to the text domain. By including multiple candidates and self-supervised speech features, our approach allows the machine translation model to choose the right words and ensure precise translation using various speech samples. This strategy minimizes error spread and takes advantage of large ASR and MT datasets, along with pre-trained ASR/MT models, while addressing associated issues.