Microsoft Speech API Research Articles

Topic Identification in Voice Recordings

Abstract The paper shows the understanding of a topic recognition problem like the speech recognition system based on Natural Language Processing (NLP) and the steps of its implementation of a rules-based approach, which is able to classify given audio materials based on predefined topics in real-time. During implementation, a statistical vocabulary was developed. Google Speech API (Application Programming Interface) was employed for subtitling audio materials, and the most ideal time frame for reception was identified through several experiments. The motivation of this work is based on the deficiency of similar simple systems for Hungarian topic recognition, even though numerous international languages already utilize multiple Automatic Sound Recognition (ASR) systems.

IMPROVING THE IMAGE-TO-SPEECH SYSTEM ACCURACY THROUGH INTEGRATION OF OPTICAL CHARACTER RECOGNITION AND LANGUAGE PROCESSING TECHNIQUES

Image-to-speech systems are a type of technology allowing for the conversion of visual information, such as images or videos, into auditory output. These systems use complex algorithms and machine learning techniques to recognize and describe visual content, allowing individuals who are visually impaired or blind to access in-formation that would otherwise be inaccessible to them. Image-to-speech systems are becoming increasingly sophisticated and can be integrated into a variety of devices, from smartphones to smart glasses. This article presents an approach to improving the accuracy of the image-to-speech system by incorporating multiple techniques. The proposed system begins by using Tesseract, an optical character recognition (OCR) engine, to extract text infor-mation from images. However, OCR is often imperfect and produces errors, which can impact the accuracy of image-to-speech models. To address this issue, the Text-Davinci-002 engine was applied for post-processing OCR output, which can help to correct errors and improve the accuracy of the extracted text. Finally, the Microsoft Speech API was employed in order to generate speech from the extracted text. By integrating these three techniques, image-to-speech system accuracy was significantly improved. An example of the generated synthetic dataset showed that the proposed techniques improve image-to-speech system accuracy both on word and character levels, and also perform punctuation error correction. This approach can be useful in various applications, including reading text from images, translating written text to speech, and assisting people with visual im-pairments.

End-to-End Lip-Reading Open Cloud-Based Speech Architecture.

Deep learning technology has encouraged research on noise-robust automatic speech recognition (ASR). The combination of cloud computing technologies and artificial intelligence has significantly improved the performance of open cloud-based speech recognition application programming interfaces (OCSR APIs). Noise-robust ASRs for application in different environments are being developed. This study proposes noise-robust OCSR APIs based on an end-to-end lip-reading architecture for practical applications in various environments. Several OCSR APIs, including Google, Microsoft, Amazon, and Naver, were evaluated using the Google Voice Command Dataset v2 to obtain the optimum performance. Based on performance, the Microsoft API was integrated with Google’s trained word2vec model to enhance the keywords with more complete semantic information. The extracted word vector was integrated with the proposed lip-reading architecture for audio-visual speech recognition. Three forms of convolutional neural networks (3D CNN, 3D dense connection CNN, and multilayer 3D CNN) were used in the proposed lip-reading architecture. Vectors extracted from API and vision were classified after concatenation. The proposed architecture enhanced the OCSR API average accuracy rate by 14.42% using standard ASR evaluation measures along with the signal-to-noise ratio. The proposed model exhibits improved performance in various noise settings, increasing the dependability of OCSR APIs for practical applications.

The assessment of interprofessional practice in mental health nursing with ethnographic observation and social network analysis: a confirmatory and bibliometric network study using VOSviewer.

Despite numerous techniques for assessing mental health nursing abilities and accomplishments, most practice in psychiatric wards is based on observable clinical behaviours and actions. VOSviewer can perform bibliographic network analysis (BNA), extracting all central topics that identify core behavioural skills in mental health nursing and essential elements in interprofessional practice (IPP). The current study captures the critical concepts in mental health nursing assessment by performing a BNA of essential topics on ethnography, social network analysis, and interprofessional care. A qualitative BNA with a VOSviewer extracted relevant topics from a total of 542 articles obtained from Microsoft API. A subsequent confirmatory quantitative analysis with NVIVO weighed the percentages of the relevant issues and words extracted by the VOSviewer. Boolean keywords searched were 'ethnography,' 'social network analysis,' 'interprofessional', 'psychiatry' and 'hospital'. Major themes identified in ethnography, IPP, and social network analysis for nursing assessment were those of 'communication' (11.63%), 'whole' (9.29%), 'knowledge' (7.66%), 'person' (7.52%), 'activity' (6.31%) and 'collaboration' (6.10%). The current study has proven the value of BNA in extracting relevant topics in target literature. VOSviewer captured salient issues in mental health nursing assessment, including ethnographic observations, social network analysis, and IPP. The results confirmed the value of focusing on collaborative care, reciprocity, knowledge management, and information sharing in assessing mental health nursing performances.

Proposed speech recognition interface framework using web browser

A website can only be accessed via devices that comes with both GUI which stands for Graphical User Interface and a screen. For this to be done, there must be physical attraction with such devices. This paper presents a speech recognition using web browser (SRWB) which permits browsing or surfing the Internet with the use of a standard voice only and VUL (Vocal User Interface development). The SRWB system input from the users in form of vocal commands and coverts these voice commands to HTTP requests. The SRWB system will sends the voice commands to the web server for processing purposes and when the processing is done, the converted or translated HTTP response is outputted to the end users in a voice format made audible with the attached loudspeakers. The system uses the Speech Application Programming Interface which is known in short as SAPI. SAPI which was developed by Microsoft allows SRWB to be used in the Windows applications. This algorithm is implemented by the system to achieve its target over content of the web to classify, analyse and send back important part of web pages to the end users. Speech recognition is used for controlling web browsers and applets, enhancing the internet, and filling out forms in numerous ways. Through speech synthesis, web pages are brought back to live, reduces audio that are sent over the internet. SRWB has many applications such as assisting the blind people to make use of the internet via speech and hearing. It will help both the young children and people with disability who can’t operate a keyboard to use the internet by just speaking. It grants enablement to people to interface the website contents through oral or audio commands instead of using a keyboard. For this system Microsoft access and SQL were used as databases while Visual Basic.NET was the programming environment used for developing and designing. SRWB is very easy to use, visually independent and can be used by anyone that is not computer literate.

Performance Analysis: AI-based VIST Audio Player by Microsoft Speech API

Speech recognition has gained much attention from researchers for almost last two decades. Isolated words, connected words, and continuous speech are the main focused areas of speech recognition. Researchers have adopted many techniques to solve speech recognition challenges under the umbrella of Artificial Intelligence (AI), Pattern Recognition and Acoustic Phonetic approaches. Variation in pronunciation of words, individual accents, unwanted ambient noise, speech context, and quality of input devices are some of these challenges in speech recognition. Many Application Programming Interface (API)s are developed to overcome the issue of accuracy in a speech-to-text conversion such as Microsoft Speech API and Google Speech API. In this paper, the performance of Microsoft Speech API is analyzed against other Speech APIs mentioned in the literature on the special dataset (without background noise) prepared. A Voice Interactive Speech to Text (VIST) audio player was developed for the analysis of Microsoft Speech API. VIST audio player creates runtime subtitles of the audio files running on it; the player is responsible for speech to text conversion in real-time. Microsoft Speech API was incorporated in the application to validate and make the performance of API measurable. The experiments proved the Microsoft Speech API more accurate with respect to other APIs in the context of the prepared dataset for the VIST audio player. The accuracy rate according to the precision-recall is 96% for Microsoft Speech API, which is better than previous ones as mentioned in the literature.

APLIKASI PERINTAH SUARA UNTUK OPERASI POWERPOINT

Microsoft PowerPoint merupakan aplikasi yang sering dipakai dalam presentasi dikarenakan kemudahan pengoperasiannya. Meski begitu, pengguna masih diharuskan untuk mengatur jalannya presentasi secara manual seperti memulai slide, meneruskan ke slide selanjutnya, kembali ke slide sebelumnya, dan sebagainya dengan menekan tombol di keyboard. Sering kali, sulit bagi pengguna meraih komputer saat sedang melakukan presentasi di depan orang banyak dan tentu akan memakan waktu. Tujuan penelitian ini adalah untuk mengurangi kontak fisik antara pengguna dengan komputer dengan menggunakan suara sebagai pengganti perintah keyboard untuk mengatur jalannya presentasi sehingga lebih efektif. Penelitian ini mengimplementasikan Hidden Markov Models dasar Microsoft Speech API dengan bahasa pemrograman C#. Tingkat toleransi perubahan pola kata yang mendekati kata asli adalah 84,29% serta akurasi jalannya program dalam latar suara jernih adalah 100%. Pengguna bisa menggunakan aplikasi dengan mikrofon atau semacamnya sebagai input yang sesuai dengan komputer mereka.

Assessing personal exposure to urban greenery using wearable cameras and machine learning

Urban greenery is closely related to people's behaviour. With the advancement of science and technology in Artificial Intelligence, wearable sensors and cloud computing, the potential for studying the relationship between people and urban greenery through new data and technology is constantly being explored, such as assessing population exposure to urban greenery using multi-source big data. Taking one individual participant as a case study, this paper proposes and validates the effectiveness of using wearable camera (Narrative Clip 2) and machine learning (Applications Programming Interface of Microsoft Cognitive Service) to assess personal exposure to urban greenery. Microsoft API is used to identify urban greenery tags, including “flower”, “forest”, “garden”, “grass”, “green”, “plant”, “scene” and “tree”, in personal images taken by the wearable camera. Personal exposure to urban greenery is assessed by calculating the frequency of the urban greenery tags in all the images taken. Furthermore, the overall evaluation and regularity of personal exposure to urban greenery (including “static exposure” and “dynamic exposure”) are explored to identify the characteristics of individual's greenery lifelogging. This study makes a brave attempt that may contribute a new perspective in applying personal big data in studying individual behaviour.

SMART-In English: Learn English Using Speech Recognition

English is an international language and important to learn. For someone learning English sometimes is a difficulty, especially in pronunciation. Therefore, SMART-In is a prototype of Android App that uses Speech Recognition technology by utilizing services from the Cloud Speech API (Application Programming Interface). SMART-In English can be used as an alternative to English learning, especially in the pronunciation of a word. Using speech recognition can display the score of the pronunciation spoken by the user, recorded, show a level the pronunciation of the word and display the correct pronunciation.

Speech Recognition Application for the Speech Impaired using the Android-based Google Cloud Speech API

Those who are speech impaired (tunawicara in the Indonesian language) suffer from abnormalities in their delivery (articulation) of the language as well their voice in normal speech, resulting in difficulty in communicating verbally within their environment. Therefore, an application is required that can help and facilitate conversations for communication. In this research, the authors have developed a speech recognition application that can recognise speech of the speech impaired, and can translate into text form with input in the form of sound detected on a smartphone. By using the Google Cloud Speech Application Programming Interface (API), this allows converting audio to text, and it is also user friendly to use such APIs. The Google Cloud Speech API integrates with Google Cloud Storage for data storage. Although research into speech recognition to text has been widely practiced, this research try to develop speech recognition, specially for speech impaired's speech, as well as perform a likelihood calculation to see the factor of tone, pronunciation, and speech speed in speech recognition. The test was conducted by mentioning the digits 1 through 10. The experimental results showed that the recognition rate for the speech impaired is about 80%, while the recognition rate for normal speech is 100%.

SALT – MARKUP LANGUAGE FOR SPEECH-ENABLED WEB PAGES

Activities to develop Lithuanian Web pages for speech-enabled access from telephone are presented. After the integration of Lithuanian text-to-speech synthesizers “Aistis” and LtMBR to SAPI 5 (Speech Application Programming Interface), some Lithuanian speech-enabled Web pages were prepared (www.speech.itpi.ktu.lt). Two methods of SALT (Speech Application Language Tags) technology implementation to Web pages are presented. First attempts to master Microsoft Speech Server’2004 are discussed.

SISTEM PAKAR DIAGNOSA PENYAKIT AYAM MENGGUNAKAN PERINTAH SUARA

This research was conducted based on the need for a tool for farmers and extension workers in diagnosing the disease in chickens. The tools in the form of an expert system which in addition to diagnosis is also able to provide medical advice. This expert system in the consultation can be run using voice commands to answer every question with a yes or no vote. The process of speech recognition using SAPI (Speech Application Programming Interface) is a tool that is used to process the analog sound is then converted to text. Inference method used is backward chaining with the model of Depth First Search. The output of this system in the form of the name of the disease and treatment suggestions.

Implementation of a Voice-ControlSystem for Issuing Commands in a Virtual Manufacturing Simulation Process

Speech recognition is a technology that attempts to involve audio cues during interaction with machines, instead of being limited to just visual and touch interfaces. However, a keyboard and mouse input is an archaic method of interaction, adding on to the fact that voice control is seemingly more natural. This study aims to implement speech recognition as a form of machine control to perform simple commands in a virtual simulation process. The simulation system is an in-house developed augmented reality robotic work cell which includes a robot arm, a conveyer belt, a computer numerical control (CNC) machine, and a pellet. Issuing commands are performed via the Windows Speech Recognition software built from the Microsoft Speech Application Programming Interface (SAPI). This software is advantageous because it can be fairly accurate once trained properly, is easily modifiable by anyone regardless of the operator’s programming knowledge, and is free. A macros tool is used to support the additional features of the recognition software which includes directly programmable Extensible Markup Language (XML) codes.

PENERAPAN ALGORITMA ARI BORNEO (AB) UNTUK PEMBACAAN TEKS DENGAN MEMANFAATKAN MICROSOFT SPEECH DAN ID1

Reading is an activity person to obtain information from something written. Reading involves recognition of the symbol and the letters that make a language. But there are some people who are lazy to read text in English language which is not a language that is used everyday by Indonesian people. In addition to reading, there are also the most common activities to obtain information that is heard. Hear is a way to gain an understanding of the meaning of the information in the form or sound using auditory senses. Reading activities contributed 10% ability for know information, with listening, knowing information can reach 30%. With conditions like this, then it needs an alternative media that can help treat the condition. The alternative media that can be made is text to speech fo r read text in Indonesia language and English language, for detection language using Ari Borneo Algorithm. These systems are made using Delphi 7 programming language, MBROLA Tools as Indonesia-speaking sound generators and Microsoft Speech API as English sound generator. Through this system, userscan absorb information from listening to the reading o f text by both systems.

Development of a Text-Dependent Speaker Recognition System

Speaker recognition is the ability of recognizing a person based on his voice. Many modalities and techniques have been applied to achieve the task of authentication, ranging from retina scans to finger prints. This paper presents a TextDependent model for automatic Speaker Recognition. Features extractor are based on Mel-Frequency Cepstrum Coefficients (MFCCs) and Linear Predictive Coding (LPC) analysis technique which aids the translation of incoming speech into a feature value. Also, a recognizer block, employs the two techniques (MFCC and LPC) to get an hybrid features for speaker identification/verification system. An experiment was carried out on the threshold from 75% to 95% at 5% differential to know the performance of the MFCCs and LPC identification/verification system. From the experiment carried out, the result shows that LPC outperforms MFCCs and a combination. The text-dependent speaker recognition system was implemented using Java Programming Language (Java Speech Application Programming Interface (JSAPI) ). The system is developed for access control into computer systems and could be used for access control where security is considered to be of utmost important.

Application of Human-Computer Speech Interaction in Dispatching System

With the rapid development of power market, the intelligent dispatching plays a central role, so that the dispatchers are in the presence of a great quantity of challenges. In order to lessen the dispatchers’ burden and raise the working efficiency, this paper proposes a project of integrating the speech technology into the intelligent dispatching system. The project is designed and implemented on the Microsoft Speech API (SAPI) platform. The main components of the system are speech training, grammar compilation, speech recognition, keyword extraction, inquiry backstage and speech synthesis. In the next stage, optimizing grammar and building high performance will be paid more attention.

Research and Design of Electronic Speech Reader Based on Text-to-Speech Technology

TTS, namely text-to-speech, is a kind of technology who can convert text information into sound signal according to information Speech processing rules. TTS, as the synthetic technology of the pronunciation, is the key technology in the current development of computer technology, and one of the most forward technical in its voice service, telephone banking, and information home appliances, mobile PDA fields. TTS has its extensive applications. In this paper, TTS is applied to electronic speech reader, which changes traditional way to read e-book, and both listening to and novels and learning English. This article introduces a method about how to make use of TTS technology, and how to achieve an electronic Speech reader of programming based on Visual Studio C# 2008 environment bring API and Microsoft SAPI interface.

A novel Wake-Up-Word speech recognition system, Wake-Up-Word recognition task, technology and evaluation

Wake-Up-Word (WUW) is a new paradigm in speech recognition (SR) that is not yet widely recognized. This paper defines and investigates WUW speech recognition, describes details of this novel solution and the technology that implements it. WUW SR is defined as detection of a single word or phrase when spoken in the alerting context of requesting attention, while rejecting all other words, phrases, sounds, noises and other acoustic events and the same word or phrase spoken in non-alerting context with virtually 100% accuracy. In order to achieve this accuracy, the following innovations were accomplished: (1) Hidden Markov Model triple scoring with Support Vector Machine classification, (2) Combining multiple speech feature streams: Mel-scale Filtered Cepstral Coefficients (MFCCs), Linear Prediction Coefficients (LPC)-smoothed MFCCs, and Enhanced MFCC, and (3) Improved Voice Activity Detector with Support Vector Machines. WUW detection and recognition performance is 2514%, or 26 times better than HTK for the same training & testing data, and 2271%, or 24 times better than Microsoft SAPI 5.1 recognizer. The out-of-vocabulary rejection performance is over 65,233%, or 653 times better than HTK, and 5900% to 42,900%, or 60 to 430 times better than the Microsoft SAPI 5.1 recognizer. This solution that utilizes a new recognition paradigm applies not only to WUW task but also to any general Speech Recognition tasks.

Voice activated command and control with speech recognition over WiFi

This paper presents work conducted to date on the development of a voice activated command and control framework specifically for the control of remote devices in a ubiquitous computing environment. The prototype device is a Java controlled Lego Mindstorm robot. The research considers three different scenario configurations. A recognition grammar for command and control of the robot has been created and implemented in Java, in part in the recognition engine and in part on the robot. The physical topology involves Java at each node endpoint, that is, at the handheld PC (iPaq), the PC workstation, the Linux server and onboard the robot (including its Java based Lejos OS). Network communications is primarily WLAN with an element of IR where the robot is concerned. The speech recognition software used includes Sphinx4, Microsoft SAPI and the Java Speech API. We compare these speech technologies and present their benefits in the context of this research. For each given scenario we present and discuss the implementation challenges encountered and their corresponding solutions, including future plans to create additional grammars to extend the framework’s range of devices.