4 results about "Speech retrieval" patented technology

The invention discloses a video content retrieval method and device based on television system voice interaction and a terminal, and relates to the technical field of video processing, and the method comprises the steps: when a video is played for the first time, extracting a picture frame from the video at a preset frequency, converting the picture frame into a multi-dimensional image feature vector and a corresponding video timestamp, and carrying out hierarchical storage in a database, constructing vectorized data containing visual semantic information; obtaining a voice retrieval instruction, performing intention recognition and semantic understanding, extracting a detection keyword, and generating a multi-dimensional retrieval feature vector; calculating a matching degree between the multi-dimensional retrieval feature vector and a multi-dimensional image feature vector of a video picture frame stored in a database, and screening out picture frames of which the similarity is higher than a preset similarity threshold to form a retrieval candidate matching set; and determining matched picture playing. The video content retrieval method is efficient, accurate and high in interactivity, and retrieval experience and operation efficiency of the user in the video watching process are remarkably improved.

The invention discloses a video clip retrieval processing method based on voice interaction and a terminal, and relates to the technical field of intelligent terminals, and the method comprises the following steps: obtaining a voice retrieval instruction for retrieving a video clip; analyzing the voice retrieval instruction to obtain a video clip retrieval requirement; generating a video clip structured retrieval condition according to the analyzed video clip retrieval requirement; frame extraction analysis is carried out on a video needing to be retrieved, and a correlation video clip group is constructed based on continuous frame correlation and a preset duration constraint condition; according to the generated video clip structured retrieval condition, retrieving a retrieval clip corresponding to the video clip retrieval requirement from the constructed correlation video clip group; and outputting the retrieved retrieval fragment corresponding to the video fragment retrieval requirement. According to the method and the device, fragment-level retrieval is realized, continuous fragments with highly related contents can be accurately identified, the fragment range is displayed through differentiated UI identifiers, and the retrieval efficiency and the interaction experience of a user are remarkably improved.

Methods, systems, and related products that provide detection of media content items that are under-locatable by machine voice-driven retrieval of uttered requests for retrieval of the media items. For a given media item, a resolvability value and / or an utterance resolve frequency is calculated by a number of playbacks of the media item by a speech retrieval modality to a total number of playbacks of the media item regardless of retrieval modality. In some examples, the methods, systems and related products also provide for improvement in the locatability of an under-locatable media item by collecting and / or generating one or more pronunciation aliases for the under-locatable item.

This invention discloses a method for enhancing the robustness of a voiceprint retrieval model, belonging to the field of voiceprint retrieval. The invention aims to provide a method to enhance the robustness of systems using deep learning to build speech retrieval models, helping the system maintain relatively good performance even when subjected to adversarial example attacks. First, during a retrieval process, the relevance of the search results is ranked, and relatively relevant speech is selected. Then, the query statement is denoised. Next, using the denoised query speech, a second query is performed among the previously selected relatively relevant speech, selecting the most relevant speech from this second query as the final query result. This invention provides a method to enhance the robustness of voiceprint retrieval models in deep learning-based voiceprint retrieval systems, helping the system operate more effectively.