Do You ‘Trust’ Your Voice?

When it comes to biometrics, the first comes to our mind may be fingerprints and palmprints. Most of us usually unlock a system or log in our account with something we know, a password or perhaps an answer to a challenge questions. However, biometrics make it possible to do it based on something we are, our unique biologic features.

Voiceprint technology, also called speaker recognition technology, is one of the biometrics. In the speaker recognition technology, features of speaker’s voice can be extracted to uniquely present the person.

For fingerprint technology, the data is collected through a finger print scanner, while in speaker recognition, only a microphone is needed. Hence, it is much cheaper. The other advantage is that it can be done remotely, either through smartphone or normal phone or any equipment with a microphone in it.

However, unlike fingerprint technology, people seems to be less familiar with speaker recognition technology and they tend to think that it is not that reliable. In the link below about Voice Trust, the engineer said they already have the speaker recognition technology which can recognize a speaker no matter which language he says, that means it is text-independent. In addition, the system can recognize you either you use smartphone or high quality phones, whether you use good quality network or even when you catch a cold, the system is robust enough to recognize the speaker

What do you think about speaker recognition technology? Do you trust it? Imagine a voiceprint lock is option of your phone’s screen lock type, will you choose it or you still prefer to use password or fingerprint?



A Convenient System for Pension Insurance

Because of one-child policy, China is in an aging society now. Most of Chinese familes are 4-2-1 structure. One child, parents, 4 grandparents. In this situation, Pension Insurance is a very important topic. To grant the insurance to old people, the information collection is a basic process. The government should collect correct information to make sure every old people can benefit from the insurance and the money is not wrongly distributed.

Normally this procedure is done by visit and find out the living conditions of old people. But in this way, the working efficiency will be very low. Furthermore, later years it is important to ensure whether the person is still alive. With the development of artificial intelligent, you may think about using fingerprint collection. Fingerprint can be used as a survival certificate, it can make sure that each old people can be correctly enrolled in this system and won’t make duplicated certificate, better than just visit.

However, fingerprint system has its limits. It still could not solve the problem of working efficiency. For old people, they are not convenient in moving. Hence, a long-distance system should be made to save this kind of situation.

Luckily, the only remote biometric technology whose name is voiceprint recognition can meet this requirement quite well. It is very convenient. They don’t need to go to a fixed station to do survival authentication with this new system. Instead, make a call is enough to enroll to pension insurance system. Additionally, the processing time is short and the working efficiency will be higher.

There are companies that already made this proposal. I hope it can be put into use as soon as possible.

Source: (Chinese only)

Phone Fraud and Speaker Recognition

Early in last month, a famous Taiwanese actress was in trouble with Phone fraud, she lose over 1 million dollars. This is not the only case I’ve heard. Just in last year, another famous actress from Hong Kong, been cheated over 0.1 million dollars. The scammers gave them telephone call and fraud their money. For us, this may seems so ridiculous, but it happens a lot, normal people may also encounter those problems but they just may just feel ashamed to share with others.

As far as I am concerned, most of those cases didn’t have a good ending, the scammers just escaped with Ill-gotten gains.

However, in February of 2015, a special news attract my eyes. It says that the police of HuaiYin cracked a Phone fraud, the suspect is a male who disguise as a female in the other end of phone. The technology of speaker recognition make big contribution to the success of arrested him.

As we can see from this successful case, speaker recognition is really becomes a very important tool of Identity verification. Fingerprint technology is already very mature and been used in so many aspect in our daily life. However, every technology will have its limitation. In dealing with telecommunications fraud, voiceprint technology plays a more important role.

Since speaker recognition technology is still not a very mature technology, there are many people who don’t trust it. But I think with the development of this technology and artificial intelligent, speaker recognition will for sure be widely used and facilitate our life.


Comments and Questions from Previous Posts

In my previous blogs, they are a lot of comments about the security and difficulties of the speaker recognition. It’s time to gather all the information which I know to my followers. For example, a most common question is what if someone use a recording of the owner to unlock a door? Furthermore, if someone is very good at mimic others voice, can he unlock others voiceprint lock very easily?

A more difficult question is about using TTS (Text-to-speech). TTS is a speech synthesis system. If you have ever used google translate and click the speaker icon to listen to the voice of the text, you just used the TTS system. TTS converts normal language text into speech. The problem is that someone may record your voice to build your model and try to use a TTS speaker to unlock your voiceprint lock.

Last time, I was recommended to view a web page whose content is about security of your voice. The name is “Watch what you say, your smart-TV is listening”. It says the Samsung and Tesla smart-TV can spy on their users by voice recognition. I think this is really unsafe for the users.

I’m really curious on how the corresponding companies will solve those problems. Technically, how they build an anti-recording or anti-TTS speaker systems. In the customers side, how can they prevent their privacy not be misused by smart-TV companies or others.

If you can answer those questions in a technical way, or if you have any opinion about voiceprint privacy or related security problems, you are free to write your comment below and communicate with people interested in this topic.


SinoVoice’s Strato platform

Recently I am fond of how the technology of speaker recognition and some related technologies are going in China. SinoVoice company is the one that first attract my eyes.

SinoVoice Company is one of the earliest companies that do research on artificial intelligence technology. In particular, the speech recognition, speech synthesis, speaker recognition, natural language understanding technology are four core technologies to form a complete closed-loop intelligent voice technology ecosystem for their artificial intelligence platform named Strato.

I think SinoVoice is a very considerable company. They are the only company that has Uighur language speech recognition and speech synthesis, a language used by people from minority of China.

Another thing that I appreciate is that SinoVoice alliance with Tsinghua University, co-found the “Qing Hua Lingyun Artificial Intelligence Research Center” in 2013. Tsinghua University is the university that most of Chinese students who learn science or industry dreaming of to attend. Hence, I think SinoVoice has long-term vision and there are sure to make huge contribution in artificial intelligence technologies. In addition, the launch of the speaker recognition technology is one of the outstanding fruits of “Qing Hua Lingyun Artificial Intelligence Research Center “.

Are you also interested in the development of speaker recognition in China? Or do you already have some knowledge of how well this technology is developed in other countries all over the world? Feel free to contribute your idea here.


Voice Login In WeChat

Nowadays, WeChat is the most popular social app in China.

In 2014, WeChat released a new version in iOS. The most important trying is the addition of “voice lock” as a choice to login your account. Users can activate this function in set mode. After logoff and then log in again, the choice will appear and users can just say the numbers out and login their WeChat. But now the function is just in grey on-line phase, only part of the WeChat users can try it.

There is no doubt that the technology behind is speaker recognition. As you can see, speaker recognition can also play an important role in identify a person’s features, and this technology will be more and more applied in real life applications.

However, you must have noticed that speaker recognition is not that widely in used in internet products. There are mainly constraints that influence it. The main reason I think may be people are still not feel so safety in using it. As each time only a short utterance is used for identification and verification, the accuracy is very dependent on the technology itself. The second reason may be that it also depends on how the user speaks to it. The same user can say the same sentence in different ways without notice it. Besides, the developers have to also find solution to against the recording of people’s voice to be verified.


Nuance’s Voice Biometrics

In this blog I am going to introduce the Nuance Communications and Nuance’s voice biometrics.

Nowadays, APPLE’s device is seen everywhere, and Siri must also be familiar to most of us. With Siri, you can ask questions to your iphone or ipad by voice. Since it does not demand typing, it is very convenient to use and in ios8 there are more functions combined with Siri. But do you know where is Siri comes from? Actually, Siri was introduced by Nuance Communications, Inc.

Nuance Communications is an American multinational computer software technology corporation, headquartered in Burlington, Massachusetts, United States, a suburb of Boston, that provides speech and imaging applications (Wikipedia).

In 2014, ING introduced a voice-controlled mobile banking app. This apple was also powered by Nuance. It is aimed to offer an innovative, simple and hands-free alternative for their customers to do mobile banking. If the voice is verified, then the customer can access to his account.

Nuance also introduces “Nuance FreeSpeech” verification system to Barclay phone verification system. Now the Barclay phone verification system can use biometric technology to authenticate via voice. The voice biometrics will obtain data from a 30s conversation between call center employees and customers, and the accuracy is over 95%. They declare that over 84% of customers are trying this new service. This technology is expected to quickly cover the United States, so they do not need to call SSNs when every time they call service center.

That’s all what I’ve learned till now about Nuance’s voice biometrics. If you are interested, don’t hesitate to check the link below to learn more.