Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for generating speech spectrum

A technology of speech spectrum and speech, applied in speech analysis, speech synthesis, speech recognition, etc., can solve problems such as low complexity, achieve the effect of saving power and improving the accuracy of speech recognition

Inactive Publication Date: 2012-04-25
CERENCE OPERATING CO
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in order to work efficiently by using the limited processing and storage capabilities of the most compact electronic devices such as mobile phones, auditory feedback processing requires efficient and low-complexity algorithms

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
  • Method for generating speech spectrum
  • Method for generating speech spectrum
  • Method for generating speech spectrum

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] Before describing in detail the embodiments according to the present invention, it should be noted that the embodiments mainly relate to the combination of method steps and apparatus components for generating a speech spectrum from input text. Accordingly, apparatus components and method steps have been represented appropriately by conventional symbols in the drawings, only those specific details are shown which are relevant to the understanding of the embodiments of the invention so as not to cause any inconvenience to persons of ordinary skill in the art having the benefit of the description herein. Details that would be obvious to the skilled person obscure this disclosure.

[0016] In this document, relational terms such as left and right, first and second, etc. may be used only to distinguish one entity or action from another without requiring or implying a relationship between such entities or actions. Any actual such relationship or order. The term "comprises" o...

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 method comprises: aligning the length of phoneme correlated to the input words to multi model states; for each of the multi model states, selecting a mixing from the polyhybrid Gaussian density model state to generate a state sequence; using the state input sequence as the input words to generate voice parameter sequence.

Description

technical field [0001] The present invention generally relates to speech synthesis. In particular, but not exclusively, the present invention relates to providing synthesized speech feedback using model states, such as Hidden Markov Model (HMM) states, associated with speech recognition systems. Background technique [0002] Many speech recognition systems match input speech to acoustic models stored in a database. The matched acoustic models are then associated with entries in the dictionary database, enabling text and sentence recognition. Acoustic models typically include Hidden Markov Models (HMMs). HMMs are statistical descriptions, including mean and variance vectors, that describe units of speech such as words and phonemes. Thereafter, HMM pattern matching is used to determine whether the acoustic model in the speech recognition database matches the input speech. HMMs are usually based on probability functions comprising some complex Gaussian probability distribut...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G10L13/00G10L13/02G10L13/04G10L15/08G10L15/14
Inventor 曹振海祖漪清
Owner CERENCE OPERATING CO
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products