Speech Technology And Applications Computer Science Essay

Published: Last Edited:

This essay has been submitted by a student. This is not an example of the work written by our professional essay writers.

This paper discusses the need of speech technology and applications of using speech on mobile phones or handheld computing devices. The combination of speech and mobile is going to change the user experience. In order to assist users in managing mobile devices, user interface designers are starting to combine the traditional keyboard or pen input with "hands free" speech technologies. Speech act as a key technology for expanding the use of mobile phones.Speech is the most natural form of communication for people.People can speak much faster than they can type especially on a small mobile device.In many situations it would be safer and more convenient to speak and listen. So,the overall mobile user interfaces needs to support speech along with other modalities of input and output and allow the user to freely and easily switch between modalities depending on their preference and situation. Speech is transforming from an alternative to text input into a much more powerful tool that can connect users more quickly to information using natural language processing.Natural language processing and machine learning capabilities will be useful for mobile users,helping them to seek answers that are currently hard to come by.Speech can be build to complement and enhance other interfaces helping you to find existing applications or information. It's really powerful direct access, we're just entering an amazing era of speech. It makes more sense to move speech technology deeper into smart phones, integrating it from the ground up, which will open even more opportunities for speech to aid in the user experience.


Mobile phones have become a essential for various people throughout the world. Mobile phones are the perfect way to keep in touch with friends, family, business links and connected with others people and offer the user with a sense of security. In the incident of emergency, having a mobile phone can allow help to reach speedily and could probably save lives. However, the value of mobile phones goes way beyond personal safety. Modern mobile phones are capable of sending and receiving photos and files ,internet access and some mobile phones are outfitted with GPS technology, allow the user to locate the place in the case of loss or emergency. When mobile phones were first launched to the public, they were bulky, costly, and some even required a base unit that had to be transported all along with the phone. Good reception was a main problem and in common, early mobile phones could only be used in convinced locations were the signal was mainly strong. As mobile phone technology sophisticated, the difficult in using them became less of a trouble. Today, Mobile phone reception has turn into reliable and of high quality due to improvements in wireless technology. Wireless service suppliers offer excellent packages and promotions for mobile phone users. Finding a reliable service provider is no longer a concern for mobile phone users. The expansion of the wireless service provider industry gives mobile phone users a choice and the increased competition has caused a drop in prices of wireless mobile phone service. Over the past decade, the rising significance of cell phones has made them almost a essential for most people. Even remote and developing countries have some access to cell phone and wireless services. Cell phones have become nearly a status symbol in addition to the convenience and security .


Speech has an significant role to play in creating better interfaces on small mobile devices. It's a natural, next evolutionary step to keyboards, keypads and touch screens. Speech technology enables hands-free and eyes-free use of mobile devices for improved convenience, safety and accessibility. People can speak much quicker than they can type .In many situations it would be convenient and safer to speak and listen. The challenge of interacting with applications through a small keyboard and display can be difficult for people with various physical or sensory impairments. Speech enabled interfaces helps such users to interact various applications and service on mobile devices. So, the cell phone user interfaces needs to sustain speech along with other modalities of input and output and permit the user to freely and easily change between modalities depending on their preference and situation.Let's spot some motivations that made the speech technology important in mobile phones.

An Overburdened Graphical User Interface

The graphical user interface (GUI) on PCs has fueled its usability and growth. Most smart phones in late 2009 attempted to transplant the GUI concept to mobile phones with minimal innovation. Touch, for example, was added as an alternative pointing device, adding support for multi-finger gestures to zoom in or out and for other functionality. The transplantation was effective in giving users something familiar they could use without a user's manual, but using the GUI with a small screen and inadequate keyboard was not an easy process.

The Need for a Hands-free Option While Driving

"Distracted driving" has attracted the attention of lawmakers and regulatory

agencies. The issue is in part the misuse of mobile phones while driving. Thus, using speech technology allows hands-free control of communications devices and avoids confusion while driving. This initiates the speech interface for mobile phones.

Lack of Uniformity

Each wireless mobile phone and often each wireless provider offer a significantly different experience. A speech interface can introduce an intuitive, consistent option across many devices.


Mobile devices have greatly increased in their popularity and use in recent years, and users largely depend on smart phones for online queries and task management. As keyboard entry is cumbersome while on the move, using speech as input and output for user interaction has recently been surveyed and implemented as a natural step further for enhanced usability. Various speech applications in mobile phone is discussed below.


GPS or Global Positioning System was initially developed as a military navigation tool. However the technology has grown beside with a sub set of supporting technologies to serve other requirements within user's budgets. The GPS provides a set of geographical coordinates such as a place's longitude, latitude and elevation on Earth. The GPS also gives out very accurate time. Once a user is positioned through GPS, the place can be identified on a map. This is useful for locating a specific unit, finding a route map from one point to other point or selecting a right route in real time. Mobile phone offers full featured navigation with voice-prompted turn-by-turn directions. It also speaks street names and exits so drivers do not have to take their hands off the wheel.


Voice dialing or hands free dialing is present in almost all mobile phones. Voice dialing allows mobile users to speak a name to call a number instead of typing a number manually or picking it from a phone book.

Voice dialing are two types

Speaker dependent

Speaker independent

Speaker dependent is recorded voice dialing .In which voice dial access must be explicitly formed by speaking and recording the names. The mobile phone will alone respond to recorded names, and generally only when spoken by the same person who recorded them. The maximum number of voice dial entries is usually limited to a fraction of the size of the whole phone book. In the case of speaker-independent , no recording is required for voice recognition. The name can be called by anyone, and the mobile phone will automatically match the called name with the closest name present in the phone book.


A Voice User Interface (VUI) is a type of natural language user interface, whereby the system employed in 2-way communication with the user through Automatic speech recognition and speech synthesis . Speech is recognized by capturing and analyzing acoustic signals using various techniques, such as statistical language models. Speech synthesis occurs by combining voice sounds from a recorded database according to a computational algorithm, or by using phonological rules to text input, which is consequently passed through a synthesizer. While the former method sounds quite natural, the latter one is more intelligible to the listener. The advancement in technology makes it a capable method of addressing the limitations of requiring human resources for mobile device input. As mobile devices have advanced from clumsy and effortful mechanical interaction, a voice-driven interface appears to be the next natural step in speech technology.


Voice-to-text communication can also be supportive for those who struggle with typing on a touch screen phone. It lets users compose and respond to text messages in natural speech instead of typing. It's so quick, convenient and easy to use. In addition to creating messages, it allows users to enter text into any text based application on the mobile phone that uses text entries like SMS, MMS, email, calendar, notes, and office documents, just by using their voice.


Speech - to - Speech translation allows people to speak and listen in their own language, regardless of the language used by the person at the other end of the line. The most fascinating about this translation is that it needed no Internet connection. Using bilingual or multilingual dictionaries, it can be used wherever needed .Hence any mobile device or cell phone can be used as a personal interpretation device. Instantaneous and conversational spoken translations have been a linguistic challenge for years. Whoever takes the lead in this technology will gain a serious advantage in the Smartphone market.


Speech technology, encompassing Automated Speech Recognition and Text-to-Speech,

enables humans to interact with electronic devices through human language. It is the most human

and benign of all technologies.Speech technology embedded in cellular phones enables easier (and potentially hands-free) dialing as well as access to various functions and software applications on the cell phone through spoken natural language input. As well, it enables access to information on the internet through spoken natural language commands to the cell phone.


Speech coding is widely used today and it continues to be an important research topic. This techniques mainly aim to compress the digital speech in an efficient manner for either storage or transmission. Speech coder includes two important component called Encoder and Decoder. The first one receives the digital speech as input and produces coded speech as output with smaller bit - rate than the input signal. This compressed signal is stored in a storage device or transmitted to another device through a transmission channel and the second one decompresses the speech signal. Speech coders use technique like prefiltering , postfiltering and noise shaping in order to avoid noise that arise due to environment and coding.


Mobile phones, with their increasing processing power and memory, are enabling a diversity of tasks which demand extensive user interaction. Text input using a small keypad becomes one of the most critical usability issues for mobile interaction design.To solve the problem of text input, research has focused on Speech Technology.ASR allows users to dictate text to a mobile phone. Users' voice input is converted into text via a speech recognition engine, embedded in the cell phones.


Speech synthesizer is one of the fastest growing technologies in mobile phones. Mobile device usually have a small display and they are also often used in situations in which the user is not able to pay much attention to the screen. Using speech synthesis in such devices can provide several advantages compared to the traditional output method display. Text-to-Speech (TTS) application can read e-mail, text messages, web pages or any other text. The TTS systems is expanding fast with steady increase in quality. Mobile device with speech synthesis are also becoming more affordable for common customers, which makes these systems more suitable for everyday use.


Speech technology in mobile phones has shown remarkable amount of expansion over the past few years. But ,there is still a lengthy way to go. Researcher have to concentratr on upgrading the quality of speech coding,speech recognition and synthesis. Speech technology have to remove usability constraints from the mobile interface and allow to build more complex applications that provide better self-service capabilities.There is no doubt that speech technologies continuously evolve and provide richer user experience.Important ongoing research is to improve speech recognition or synthesis for all languages and another important area is to add emotions to speech. The major challenge is to provide user friendliness and increasing flexibility with low cost.