Relative Positional Encoding for Speech Recognition and Direct Translation
원문 초록
Transformer models are powerful sequence-to-sequence architectures that are capable of directly mapping speech inputs to transcriptions or translations. However, the mechanism for modeling positions in this model was tailored for text modeling, and thus is less ideal for acoustic inputs. In this work, we adapt the relative position encoding scheme to the Speech Transformer, where the key addition is relative distance between input states in the self-attention network. As a result, the network can better adapt to the variable distributions present in speech data. Our experiments show that our resulting model achieves the best recognition result on the Switchboard benchmark in the non-augmentation condition, and the best published result in the MuST-C speech translation benchmark. We also show that this model is able to better utilize synthetic data than the Transformer, and adapts better to variable sentence segmentation quality for speech translation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
BeaverTalk: Oregon State University's IWSLT 2025 Simultaneous Speech Translation System
Intrinsic vs. Extrinsic Evaluation of Czech Sentence Embeddings: Semantic Relevance Doesn't Help with MT Evaluation
End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data
ConECT Dataset: Overcoming Data Scarcity in Context-Aware E-Commerce MT
HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation
Explainability of Speech Recognition Transformers via Gradient-based Attention Visualization
토론
이 논문과 연결된 포럼 글이 아직 없습니다.