VAD dynamic parameter adjusting method and device

A dynamic parameter and parameter sequence technology, applied in the field of information processing, can solve problems such as failure to apply voice, low accuracy of voice endpoint detection, and failure to consider special scenarios, and achieve the effect of improving detection accuracy

CN106611598AActive Publication Date: 2017-05-03SHANGHAI XIAOI ROBOT TECH CO LTD
5 Cites 19 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2017-05-03

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a VAD dynamic parameter adjusting method and device, and the method comprises the steps: extracting an emotion feature vector of a voice signal of each sentence in a training corpus; enabling the emotion feature vector of the voice signal of each sentence to serve as the input feature of a neural network, enabling a pre-determined optimal VAD parameter sequence of the voice signal of each sentence to serve as the expected output of the neural network, employing a set neural network training algorithm, and carrying out the training of the built neural network; and carrying out the voice end point detection of a current sentence during voice processing through a VAD parameter which is outputted by the trained neural network through taking the emotion feature vector of a former sentence of the current sentence as an input feature. The method finds out the rule between the emotion information in voice and related parameters of a VAD model, obtains a VAD effective optimal parameter model, employs the optimal parameter model to carry out the dynamic pre-estimation of the VAD parameters during voice end point detection, and achieves an effect of optimizing the VAD in a special scene.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of information processing, in particular to a method and device for adjusting dynamic parameters of a voice endpoint detection VAD. Background technique

[0002] The energy double-threshold method is a commonly used algorithm for voice endpoint detection VAD. Speech signals can generally be divided into silent segments, unvoiced segments, and voiced segments. The silent segment is the segment of background noise, with the lowest average energy; the voiced segment is the segment of the voice signal corresponding to the vibration of the vocal cords, with the highest average energy; the unvoiced segment is the segment of the voice signal generated by the friction, impact or explosion of air in the oral cavity, and the average energy is between between the former two. The waveform characteristics of the unvoiced segment and the silent segment are obviously different. The signal of the unvoiced segment changes ...

Examples

Embodiment Construction

[0021] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0022] The embodiment of the present invention provides a VAD dynamic parameter adjustment method and device. The method and device use a deep neural network to learn the emotional information in the speech, find out the rules existing between the emotional information in the speech and the relevant parameters of the VAD model, and obtain the corresponding The optimal parameter model for VAD effect. When voice endpoint detection is ...