Unlock instant, AI-driven research and patent intelligence for your innovation.

A neural network embedding system for a speaker-free confirmation text

A technology of speaker confirmation and neural network, which is applied in the direction of biological neural network model, neural architecture, neural learning method, etc.

Inactive Publication Date: 2019-01-08
联智科技(天津)有限责任公司
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this approach requires a large number of trained speakers in the domain to be effective

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A neural network embedding system for a speaker-free confirmation text
  • A neural network embedding system for a speaker-free confirmation text
  • A neural network embedding system for a speaker-free confirmation text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0020] A neural network embedding system for text without speaker confirmation, such as figure 1 shown, includes a feed-forward DNN that computes speaker embeddings from variable-length segments. The structure is based on an end-to-end system. However, end-to-end approaches require a large amount of in-domain data to be effective. The end-to-end loss is replaced by a multi-class cross-entropy objective. Additionally, a separately trained PLDA backend is used to compare pairs of embeddings. This enables DNNs and similarity measures to be trained on potentially different datasets. This network can be implemented using the nnet3 neural network library in the Kaldi Speech Recognition Toolkit. The DNN can be characterized as 20-dimensional MFCCs with a frame length of 25 ms, average normalized over a sliding window of up to 3 seconds; the same energy-based VAD from segment 2 can filter out non-speech frames ; instead of stacking frames at the input, the short-term temporal con...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical field of neural networks, in particular to a neural network embedding system for a speaker-free confirmation text, the system comprising a feedforward DNN and aneural network structure. The feedforward DNN adopts an end-to-end system, and the neural network structure comprises a layer for operating a speech frame, a statistical data pool layer gathered on aframe layer representation, an additional layer for operating at a segmentation layer, and a final softmax output layer. Nonlinearity is a modified linear unit (ReLUs). The system has the ability to improve the performance of a smaller common data set so that DNN no longer trains the system to separate the same speaker and different speaker pairs, but learns to classify the trained speakers.

Description

technical field [0001] The invention belongs to the technical field of neural networks, and in particular relates to a neural network embedding system for text confirmation without a speaker. Background technique [0002] Currently, Speaker Verification (SV) is the task of verifying the claimed speaker's identity based on some speech signals and registered speaker recordings. Typically, low-dimensional representations rich in speaker information are extracted for enrollment and test utterances and compared to achieve same or different speaker decisions. In modern systems, the representation is usually an i-vector. The task is considered text-dependent if the lexical content of the utterance is fixed to a certain phrase, otherwise it is text-independent. In some practical applications, confirmation must be performed using only a limited number of test utterances to avoid delays in online applications or due to limited availability. Most text-independent SV systems are base...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/044G06N3/045
Inventor 刘晓鹏吴晋
Owner 联智科技(天津)有限责任公司