arXiv:1912.04784
A Novel Topology for End-to-end Temporal Classification and Segmentation with Recurrent Neural Network
원문 초록
Connectionist temporal classification (CTC) has matured as an alignment free to sequence transduction and shows competitive for end-to-end speech recognition. In the CTC topology, the blank symbol occupies more than half of the state trellis, which results the spike phenomenon of the non-blank symbols. For classification task, the spikes work quite well, but as to the segmentation task it does not provide boundaries information. In this paper, a novel topology is introduced to combine the temporal classification and segmentation ability in one framework.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine
NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech
WhisperKit: On-device Real-time ASR with Billion-Scale Transformers
VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis
A Hybrid Machine Learning Framework for Optimizing Crop Selection via Agronomic and Economic Forecasting
AUTOMATIC PRONUNCIATION MISTAKE DETECTOR PROJECT REPORT
토론
이 논문과 연결된 포럼 글이 아직 없습니다.