SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition
원문 초록
The Transformer architecture has been well adopted as a dominant architecture in most sequence transduction tasks including automatic speech recognition (ASR), since its attention mechanism excels in capturing long-range dependencies. While models built solely upon attention can be better parallelized than regular RNN, a novel network architecture, SRU++, was recently proposed. By combining the fast recurrence and attention mechanism, SRU++ exhibits strong capability in sequence modeling and achieves near-state-of-the-art results in various language modeling and machine translation tasks with improved compute efficiency. In this work, we present the advantages of applying SRU++ in ASR tasks by comparing with Conformer across multiple ASR benchmarks and study how the benefits can be generalized to long-form speech inputs. On the popular LibriSpeech benchmark, our SRU++ model achieves 2.0% / 4.7% WER on test-clean / test-other, showing competitive performances compared with the state-of-the-art Conformer encoder under the same set-up. Specifically, SRU++ can surpass Conformer on long-form speech input with a large margin, based on our analysis.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization
Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models
Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASR
Improving Named Entity Transcription with Contextual LLM-based Revision
Automatic Speech Recognition of African American English: Lexical and Contextual Effects
Customizing Speech Recognition Model with Large Language Model Feedback
토론
이 논문과 연결된 포럼 글이 아직 없습니다.