Finding phonemes: improving machine lip-reading
원문 초록
In machine lip-reading there is continued debate and research around the correct classes to be used for recognition. In this paper we use a structured approach for devising speaker-dependent viseme classes, which enables the creation of a set of phoneme-to-viseme maps where each has a different quantity of visemes ranging from two to 45. Viseme classes are based upon the mapping of articulated phonemes, which have been confused during phoneme recognition, into viseme groups. Using these maps, with the LiLIR dataset, we show the effect of changing the viseme map size in speaker-dependent machine lip-reading, measured by word recognition correctness and so demonstrate that word recognition with phoneme classifiers is not just possible, but often better than word recognition with viseme classifiers. Furthermore, there are intermediate units between visemes and phonemes which are better still.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Re-synchronization using the Hand Preceding Model for Multi-modal Fusion in Automatic Continuous Cued Speech Recognition
Resource aware design of a deep convolutional-recurrent neural network for speech recognition through audio-visual sensor fusion
Transforming faces into video stories -- VideoFace2.0
Lend a Hand: Semi Training-Free Cued Speech Recognition via MLLM-Driven Hand Modeling for Barrier-free Communication
Personalized Lip Reading: Adapting to Your Unique Lip Movements with Vision and Language
LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Tasks
토론
이 논문과 연결된 포럼 글이 아직 없습니다.