Speech intelligent interaction system

Abstract

The invention relates to a speech intelligent interaction system, more particularly to an intelligent feel speech dialogue and timing play learning system, which is capable of carrying out a man- machine dialogue that is a multi-level speech dialogue. The system is composed of a content storage play module (1), a speech microphone collector (2), a starting device module (3), a play system (4), and a speech identification processing chip (5); the speech identification processing chip (5) and the speech microphone collector (2) are connected with the content storage play module (1); the content storage play module (1) is connected with the play system (4); and the starting device module (3) and the content storage play module (1) are mutually connected. According to the invention, a learning or an entertainment content can be started and played at a fixed time; besides, the system has advantages of simple structure, high recognition rate, and good anti-noise performance and high recording / playing quality; moreover, the system can be downloaded and updated freely.

Description

Technical field: [0001] The invention relates to an intelligent touch voice dialogue and timing play learning system capable of man-machine dialogue of multi-level voice dialogue, in particular to a voice intelligent interactive system with a micro SD card storage scheme. Background technique: [0002] Speech recognition technology, also known as Automatic Speech Recognition (ASR), aims to convert the lexical content of human speech into computer-readable input, such as keystrokes, binary codes, or character sequences. Unlike speaker identification and speaker verification, the latter attempts to identify or identify the speaker who uttered the speech rather than the lexical content contained within it. Applications of voice recognition technology include voice dialing, voice navigation, indoor equipment control, voice document retrieval, simple dictation data entry, etc. Speech recognition technology can be combined with other natural language processing technologies such ...

AI Technical Summary

Problems solved by technology

[0004] With the expansion of the application field, the constraints on speech recognition such as small vocabulary, specific people, and isolated words need to be relaxed. At the same time, it also brings many new problems: First, the expansion of the vocabulary makes the selection of templates difficult. Second, in continuous speech, there is no clear boundary between each phoneme, syllable, and word, and each pronunciation unit has a co-articulation phenomenon that is strongly affected by the context; third, non-specific person recognition When different people say the same words, the corresponding acoustic characteristics are very different. Even if the same people speak the same words at different times, physiological and psychological states, there will be great differences; fourth, the recognition Background noise or other distractions in speech

Therefore, the original template matching method is no longer applicable

Images