SinoVoice’s Application on Mobile Phones--part 2

[alexstary]

2.3 application software of eJASR on mobile phones
2.3.1 Voice telephone book
Voice telephone book deploys SinoVoice’s embedded Automatic Speech Recognition technology – eJASR, which is a software enabling voice dialing service for mobile phones.

2.3.1.1 Acquiring voice dialing function
There are two ways to do it: 1. Pre-install the voice dialing function onto mobile phones in the manufacturing process; 2. Download this program from the operator’s website onto the mobile phone

2.3.1.2 The process of realizing voice dialing
a) Enter the dialing program from picture one
b) Say the correspondent’s name when hear the reminder ‘Please say the name’.
c) System will operate and locate several similar names based on the voice; the first name is the priority.
d) If the first is correct and that person has only one number, the user can press the key to dial number or the system will dial automatically in a default period and connect the conversation. If that person has more than one numbers, the system will initiate ‘personal phone book’. The user can choose the right number and dial it.
e) If the first one is not correct, there is a correct name in the following options, press the up and down key to choose the correct one, press a key and make phone call. If the person has more than one contact number, it will start ‘personal phonebook’, you can choose and dial.
f) If all the options are not correct, press Key C and return to picture one.

2.3.1.3 The process of searching number with voice
a) Get into the searching program from picture one
b) When hear the reminder ‘please say the name’, say the name you want to call
c) They system will calculate and list several names that are similar to the name you said, the first is the priority
d) If the first one is correct, press a key to open the content interface or the system will display that record in the default time; if you want to call the person you can press ‘call’ key to dial and speak with the person.
e) If the first name is not right, there is a correct one in the following names, press the up and down key to choose the correct one. Press a key to display the content of that person. If you like you can press ‘call’ key to dial and speak with the person.
f) If all the names are not correct, press key ‘C’to return to the first interface

2.3.1.4 Add new name
a) Enter the program of adding new names from the first interface
b) That program will start the original installed name inputting program of the mobile phone
c) After inputting the new name, it will return to the first interface

2.3.1.5 Find and edit the incomplete number：

When dialing or searching, the system will check the incomplete numbers. For example, mobile numbers beginning with ‘13’should have 11 numbers. Any phone number has less than 11 numbers is not complete.

a) （system finds out the number is not correct）the system remind ‘the information is not complete, do you want to complement it? [The answer is limited to ‘complement’ and ‘do not complement’.]
b) （if answer ‘complement’）——start the editor and edit the content. After editing the system will check the completeness. If it’s invalid, it will go back to the previous step
c) （If answer ‘do not complement’）——the system remind: ‘ the information is not complete, exit now’, return to the first interface

2.3.2 Voice command navigation
Voice command is software that deploys SinoVoice’s embedded Automatic Speech Recognition technology –eJASR. It can enter any menu, sub-menu or execute other command with human voice.

2.3.2.1 About the start of voice command navigation
There are three methods to choose from: Hard start (Press for one time and receive for one time in default time); Soft start (have a repeatable switch on desktop or in the task bar, such as the ‘Insert’ key); Always switched on (Intelligent, as long as the voice is about the system, the pronunciation is clear and the volume is loud enough)

 Hard start（recommended）
Press a set key, voice input for one time and press for one time. It will shuts down in 3 to 5 seconds. If press again, it will start again.
Advantages：Clear command and status, switch into the shut-down mode in time, and reduce the input memory load. It’s easy to switch to other input methods.

 Soft start
The so-called ‘soft start’ is a set status. After confirmation, it has two statuses: ‘valid’ and ‘invalid’ and can switch between these statuses. The switch function can avoid inputting useless information. The status may also be changed by pressing a specific key or by voice command.
Advantages：Save a self-installed key of the device, or enhance the compatibility of software and hardware.（some system has surplus keys, some doesn’t）

 Always switched on
This is an intelligent voice navigation method, just like people’s neural reflex system.

People are receiving external audio information all the time, while they can tell what is related to them, what has nothing to do with them; or what is some basic information, what is command information.
The audio physical basis for the ‘always switched on’ status is that when people talk and when they give command, their speech is different in emphasis, tone, grammar and dividing sentences, which should be easily told apart.

The restriction for this status is the calculation capability of the system – whether it can meet the requirement or not.

2.3.2.2 Lists for voice navigation

Listed reminder is an important aspect of this product. Its main function is to list all the menus, sub-menus and other related orders on the basis of one order. It makes the route clearer and provides standard terms for command, which clarify user’s next command.
 Example for command
Example 1）The first command: “Mail System”
List：
In-box （list how many mails in-box. How many are unread）
Out-box
Compose new email
Contact
Example 2）Game software（The following listed the included games）
Solitaire
Poker
Digging gold
……
 Circumstances without list
Under some circumstances, there is no list, e.g. ‘sweep the desktop’, ‘re-start the system’, ‘shut off’, etc. they don’t have sub-menus
2.3.2.3 Word study of voice navigation
There are two aims for setting word study function for voice navigation, the first is to complement new words appearing in the development of desktop system, the second is to change the command when the user want to use his accustomed command terms.

 Add new words
There is some difficulty in adding new words. It basically is a recording process. It records as it operates. It record a certain sentence to a certain menu, until the recording process ends.

 Change the present words
It is relatively easy to change the present words. Basically it takes out a present order and input a new term for the command.

3. Cooperation modes

SinoVoice values and respects its clients. It has worked hard to develop cooperative partners to extend business together and get mutual benefit. In the authorization mode of software, there are Quantitative authorization, yearly authorization, Outright Authorization and other cooperative modes. We have different price systems for different cooperative modes, taking full consideration of the technical characteristics of products, the market life cycle and other elements to protect the mutual interests of both parties, ensuring high efficiency and integrity.

SinoVoice provides products in the following modes：

 Provide SDK for the three core technologies: Embedded Handwriting Recognition – eJHWR、 Embedded Text-to-speech – eJTTS、 Embedded Automatic Speech Recognition – eJASR，and can transplant it onto other platforms.

 Provide Handwriting input software、Short message reader、Mobile phone reader、voice phonebook、voice command navigationetc. and other mobile phone application software.

 We provide personalized mobile phone application software for customers based on the three core technologies as eJHWR、eJTTS and eJASR, of which SinoVoice has independent property rights.

For example, based on the embedded handwriting recognition technology – eJHWR, we can make customized recognizable word library for the customer, add new words and gesture symbols, and compress the recognition library to meet customer’s demand for the memory and recognition speed, or expand the recognition library to meet customer’s demand for recognition rate.

For another example, based on the embedded Text-to-speech technology – eJTTS, we can provide voice in different styles, voice library of different sizes and up-level applications, etc.

4. Contact

Beijing InfoQuick SinoVoice Speech Technology Corporation
Address ：206 10th building of ZPark, HaiDian District, Beijing, China
Post code：100094
Phone ：+86-10-82826886
Fax ：+86-10-82825830
Website ：½Ýͨ»ªÉùÓïÒô¼¼ÊõÓÐÏÞ¹«Ë¾
Email ：diqing@sinovoice.com.cn
zhaomiao@sinovoice.com.cn
marketing@sinovoice.com.cn

More Contact，More Possibility！