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

Speech synthesis device, method and monitor applied thereby

A speech synthesis and speech library technology, applied in speech synthesis, speech analysis, instruments, etc., can solve problems such as affecting the quality of synthesized speech and increasing power consumption, and achieve the effect of avoiding delay and improving quality

Inactive Publication Date: 2012-09-19
SHENZHEN MINDRAY BIO MEDICAL ELECTRONICS CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the processor core of the system needs to handle fewer tasks, the frequency of voice distortion can also be reduced by increasing the main frequency of the system, but generally it takes more than 100 MHz to achieve better voice, and increasing the main frequency will cause the system The power consumption is greatly increased (because the power consumption is proportional to the main frequency)
However, if there are too many system tasks, the complete distortion of voice cannot be completely avoided by increasing the main frequency of the system.
[0004] It can be seen from the above that due to the low-level interrupt method used in the PWM synthesis speech process, there is inevitably a certain delay in the speech processing process, and the delay will inevitably affect the quality of the synthesized speech, so it is necessary to improve the existing PWM synthesis technology

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
  • Speech synthesis device, method and monitor applied thereby
  • Speech synthesis device, method and monitor applied thereby
  • Speech synthesis device, method and monitor applied thereby

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Embodiment 1: as Figure 5 As shown, the data filling mechanism unit 230 in this embodiment is set inside the IC integrated chip. For example, this embodiment uses ADI's ADSP-BF531 high-performance Blackfin processor up to 600MHZ. The ADSP-BF531 processor has a serial port, three counter / timers with PWM (pulse width modulation) and pulse measurement capabilities, a real-time clock, a core timer, an on-chip memory up to 148Kbytes, event controller, etc. and other peripherals. The event controller consists of two parts: the core event controller (CEC) and the system interrupt controller (SIC). The core event controller (CEC) and the system interrupt controller (SIC) work together to control the priority and control all system events . Generally speaking, interrupts from peripherals enter the SIC, and then are directly sent to the general interrupt of CEC for processing. The system interrupt controller SIC provides mapping and routing to the CEC general interrupt input f...

Embodiment 2

[0031] Embodiment 2: as Image 6 As shown, the difference between this embodiment and the above-mentioned Embodiment 1 is: the data loading mechanism unit 230 in this embodiment is composed of two parts: the data loading controller 232 and the peripheral interrupt source 233 as the first priority interrupt source Here, the peripheral interrupt source 233 is set outside the IC integrated chip for implementing speech synthesis, and is composed of an off-chip timer or counter, and the event attribute of the interrupt source is set as a non-maskable interrupt. During the working process of the PWM speech synthesis device in this embodiment, the peripheral interrupt source 233 will send an interrupt request to the processor core 221 through the event controller 222 at regular intervals, and send a control signal to the data filling controller 232 . The PWM speech synthesis device of this embodiment can also be implemented by using ADI's ADSP-BF531 high-performance Blackfin processo...

Embodiment 3

[0032] Implement 3: on the basis of embodiment 1 or 2, such as image 3 As shown, the PWM converter 240 of the present embodiment includes: a counter and a comparator; the counter counts according to a certain cycle cycle, and regularly inputs digital voice data at one input end of the comparator, and at the other input end of the comparator The value of the input counter is compared with the two, and the output pulse width modulation pulse is used to drive the operational amplifier and power amplifier circuit, and the voice can be reproduced. The other components and connections of this embodiment are the same as those of Embodiment 1 or 2. If the ADSP-BF531 is also used in this embodiment, the PWM converter 240 can be realized by three timers built on and off the chip.

[0033] Based on the above scheme, the present invention also provides a monitor, which includes Figure 4 The speech synthesis device, which contains: a follow-up circuit for connecting the output end of t...

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 discloses a speech synthesis device, a method and a monitor applied thereby, the speech synthesis device comprises a speech library used for storing digital speech data to be played and a PWM converter used for carrying out pulse width modulation on the speech data; and the device further comprises a data loading mechanism unit containing a first priority interrupt source, and the data loading mechanism unit is used for interrupt processing result of the first priority interrupt source, thereby controlling the digital speech data to be sequentially loaded in the PWM converter. The invention can improve the utilization rate of the system, reduce the cost and improve the speech synthesis quality.

Description

technical field [0001] The present invention relates to speech synthesis technology, in particular to a speech synthesis device and method and a monitor applied thereto. Background technique [0002] At present, there are many kinds of voice synthesis methods, among which the output of synthesized voice in PWM mode is a low-cost and simple way of digitally synthesized voice. like figure 1 As shown, the principle of the existing PWM output speech synthesis is as follows figure 1 As shown, the received or ready-to-play digital voice data is generally stored in the voice library, and then the PWM converter in the IC integrated chip is set and the PWM event interrupt source in the PWM converter is turned on. Each PWM event interrupt source Send an interrupt request to the processor core, the interrupt request is sent to the processor core for processing through the event controller of the IC, and after the processor core responds to the interrupt request, it controls the readi...

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): G10L13/00G06F13/26
Inventor 汪生和罗军万力劢
Owner SHENZHEN MINDRAY BIO MEDICAL ELECTRONICS CO LTD