Deep Multimodal Learning for Audio-Visual Speech Recognition
원문 초록
In this paper, we present methods in deep multimodal learning for fusing speech and visual modalities for Audio-Visual Automatic Speech Recognition (AV-ASR). First, we study an approach where uni-modal deep networks are trained separately and their final hidden layers fused to obtain a joint feature space in which another deep network is built. While the audio network alone achieves a phone error rate (PER) of $41\%$ under clean condition on the IBM large vocabulary audio-visual studio dataset, this fusion model achieves a PER of $35.83\%$ demonstrating the tremendous value of the visual channel in phone classification even in audio with high signal to noise ratio. Second, we present a new deep network architecture that uses a bilinear softmax layer to account for class specific correlations between modalities. We show that combining the posteriors from the bilinear networks with those from the fused model mentioned above results in a further significant phone error rate reduction, yielding a final PER of $34.03\%$.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation Models
Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides
Visual-Aware Speech Recognition for Noisy Scenarios
Addressing Pitfalls in Auditing Practices of Automatic Speech Recognition Technologies: A Case Study of People with Aphasia
Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech
Towards Temporally Explainable Dysarthric Speech Clarity Assessment
토론
이 논문과 연결된 포럼 글이 아직 없습니다.