Multi-party call multi-mode speech synthesis method and system

Abstract

The invention provides a multi-party call multi-mode speech synthesis method, a multi-party call multi-mode speech synthesis system and a multi-party telephone call server. The method comprises such steps as decoding, unified re-sampling, silence detection, speech synthesis, echo cancellation, coding and the like, wherein in the step of speech synthesis, different speech synthesis modes are set in accordance with different path numbers of non-silence speech signals detected. The speech synthesis method disclosed by the invention not only can eliminate an overflow phenomenon but also can propose an individual sound mixing processing scheme according to actual situation through achieve statistical analysis on speech situations of various call parties, and moreover, the speech synthesis method can keep the original characteristics of the various paths of the speech signals to the greatest extent; the speech synthesis method is simple in algorithm and rapid in sound mixing, and in addition, the speech synthesis method is free from the invasion of serious noise and is capable of achieving high-quality multi-party call.

Description

technical field [0001] The invention belongs to the field of multi-party calls, in particular to a multi-mode speech synthesis method and system for multi-party calls. Background technique [0002] At present, with the development of the economy and society, the multi-party call technology capable of realizing multi-party and remote communication in real time, such as teleconferencing, is developing vigorously. In terms of voice technology for multi-party calls, the method of controlling the right to speak is traditionally used, that is, only one person is allowed to speak at a certain time, and a conference chairman is first selected in each meeting, and the speaker must apply to the conference chairman to speak before speaking Right to release the speaking right after speaking. However, this greatly limits communication between meeting members. The above-mentioned problems in the multi-party call can be solved by adopting the speech synthesis technology. Speech synthesi...

AI Technical Summary

Problems solved by technology

However, although the above scheme can weaken or eliminate the overflow phenomenon, it will greatly attenuate the mixed voice signal, increase the complexity of the algorithm, slow the mixing speed, and may introduce serious noise at the same time; and the above The solution does not conduct statistical analysis on the speeches of each speaker, and does not perform personalized mixing processing based on the statistical analysis results

Images