Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech Translation
원문 초록
The audio segmentation mismatch between training data and those seen at run-time is a major problem in direct speech translation. Indeed, while systems are usually trained on manually segmented corpora, in real use cases they are often presented with continuous audio requiring automatic (and sub-optimal) segmentation. After comparing existing techniques (VAD-based, fixed-length and hybrid segmentation methods), in this paper we propose enhanced hybrid solutions to produce better results without sacrificing latency. Through experiments on different domains and language pairs, we show that our methods outperform all the other techniques, reducing by at least 30% the gap between the traditional VAD-based approach and optimal manual segmentation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ADA-VAD: Unpaired Adversarial Domain Adaptation for Noise-Robust Voice Activity Detection
A Convolutional Neural Network Smartphone App for Real-Time Voice Activity Detection
GTTS-EHU Systems for QUESST at MediaEval 2014
에이전틱 신경망 구조 탐색
Agentic Neural Architecture Search
단순할수록 좋을 때: 중세 라틴어 필사본을 위한 번역 파이프라인 평가
When Simpler Is Better: Evaluating Translation Pipelines for Medieval Latin Manuscripts
A Diffusion-Based Kinematics and Dynamics Model for 3D Sign Language Production
토론
이 논문과 연결된 포럼 글이 아직 없습니다.