arXiv:2009.11340
The importance of fillers for text representations of speech transcripts
원문 초록
While being an essential component of spoken language, fillers (e.g."um" or "uh") often remain overlooked in Spoken Language Understanding (SLU) tasks. We explore the possibility of representing them with deep contextualised embeddings, showing improvements on modelling spoken language and two downstream tasks - predicting a speaker's stance and expressed confidence.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark
"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding
"Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding
QUADS: QUAntized Distillation Framework for Efficient Speech Language Understanding
LiveLongBench: Tackling Long-Context Understanding for Spoken Texts from Live Streams
Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks
토론
이 논문과 연결된 포럼 글이 아직 없습니다.