58 results about "Speech segmentation" patented technology

The voice print system of the present invention is a subword-based, text-dependent automatic speaker verification system that embodies the capability of user-selectable passwords with no constraints on the choice of vocabulary words or the language. Automatic blind speech segmentation allows speech to be segmented into subword units without any linguistic knowledge of the password. Subword modeling is performed using a multiple classifiers. The system also takes advantage of such concepts as multiple classifier fusion and data resampling to successfully boost the performance. Key word / key phrase spotting is used to optimally locate the password phrase. Numerous adaptation techniques increase the flexibility of the base system, and include: channel adaptation, fusion adaptation, model adaptation and threshold adaptation.

A method and system for obtaining a pool of speech syllable models. The model pool is generated by first detecting a training segment using unsupervised speech segmentation or speech unit spotting. If the model pool is empty, a first speech syllable model is trained and added to the model pool. If the model pool is not empty, an existing model is determined from the model pool that best matches the training segment. Then the existing module is scored for the training segment. If the score is less than a predefined threshold, a new model for the training segment is created and added to the pool. If the score equals the threshold or is larger than the threshold, the training segment is used to improve or to re-estimate the model.

The invention discloses a system for automatically generating animations of characters' Chinese mouth shapes. The dialogue text filtering and coding module performs phrase segmentation, pinyin mouth shape coding, overall recognition and reading mark setting and coding filtering on the dialogue text, generates and outputs dialogue mouth shape codes, and dialogue overall Recognition and reading code identification and dialogue mouth shape filter coding sequence; dialogue speech segmentation module conducts speech sampling and speech energy statistics on dialogue audio, generates and outputs dialogue speech segmentation candidate result sequence; dialogue segmentation coding integration module connects dialogue text filter coding The module and the dialogue voice segmentation module integrate and correct the dialogue voice segmentation candidate result sequence, generate and output the dialogue segmentation code sequence; the character Chinese mouth animation generation module is connected with the dialogue segmentation coding integration module, The sequence generates and outputs the character's Chinese lip animation. In the processing process of the invention, the production of the Chinese mouth animation of the whole character can be automatically completed without loading the corresponding voice library.

The invention discloses a synthesized speech detection method based on speech segmentation, which is applied in the field of speech detection. Aiming at the problem of low detection accuracy in the prior art, the present invention extracts two features in the audio: the CQCC feature of the audio segment, and the extracted audio feature The average zero-crossing rate feature of a silent (silent) segment; then use two GMM models to fit the two features respectively, and assign different weights to the two GMMs and test to find the most suitable weight; significantly improved the synthesis Speech detection accuracy.

The application provides a speech separation method, a speech separation device, electronic equipment, and a storage medium. The speech separation method includes: obtaining the original audio, and extracting the spectrogram feature sequence from the original audio in a time window sliding window; The graph feature sequence is input into the pre-trained speech segmentation model, and the embedded feature sequence is obtained through the speech segmentation model; the embedded feature sequence is input into the pre-trained speech clustering model, and the corresponding embedding feature sequence is obtained through the speech clustering model The predicted label sequence; perform single-speaker voice restoration based on the predicted label sequence to generate separated speech. According to the speech separation method, speech separation device, electronic equipment and storage medium of the present application, the problem of unsatisfactory speech separation effect can be solved, and the speech segment belonging to a single speaker can be separated from the short-term speech audio file in which multiple people speak alternately, And it can accurately estimate the number of speakers in conjunction with contextual information.

The invention provides a speech segmentation method, a device, a device and a computer storage medium, wherein the method comprises the following steps: determining the cross correlation degree of a first speech and a second speech, wherein the second speech is the speech obtained after recording the first speech, and the first speech is formed by splicing two or more first speech segments; Calibrating a time tag based on the cross-correlation, the time tag comprising a start time and an end time of each first speech segment in a first speech; Using the calibrated time stamp, the second speechis segmented to obtain more than two second speech segments. The invention can better align the calibrated time label with the second speech, thereby improving the segmentation accuracy of the secondspeech.

The video semantic scene segmentation and labeling method of the present invention includes the following steps: constructing a scene classifier based on offline training of a deep convolutional neural network based on a labeled scene image set; calculating the similarity between adjacent video frames in the video sequence Video frames are grouped according to similarity; adaptively adjust the similarity threshold to obtain video frame groups with uniform distribution of video frames; merge frame groups with too few frames, and split frame groups with too many frames to group the results of video frames Rescale; select representative video frames for each video frame grouping; use scene classifiers to identify scene categories for video frame groupings; perform semantic scene segmentation and labeling of video sequences. The present invention provides an effective means for solving the problem of video retrieval and management, and improves the user's experience and enjoyment of watching videos.