Rhythm model training method and device, electronic equipment and storage medium

• Main Author: LI RUOMING
• Format: Patent
• Language: Chinese; English
• Published: 09.03.2021
• Subjects: ACOUSTICS; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

The invention discloses a rhythm model training method and device, electronic equipment and a storage medium, and relates to the field of artificial intelligence such as the field of speech technologyand the field of deep learning. The method comprises: extracting punctuation information and rhythm information of the punctuation information in text data, establishing a mapping relation between the punctuation information and the rhythm information, obtaining first text data and second text data from the text data, labeling the first text data according to the mapping relationship to obtain corresponding training data, training the initial rhythm pre-training model according to the training data to obtain a rhythm pre-training model, and training the rhythm pre-training model according tothe second text data to obtain a rhythm model. According to the invention, the prosodic tagging efficiency is ensured, the labor cost is reduced, the tagged prosodic feature information is ensured tobe more accurate, and the m