From being a fictional element in sci-fi, voice control has become a reality, with inventions such as Apple's Siri, and interactive voice response (IVR) when calling your doctor's office. The combination of radio’s strength as a hands-free medium, public radio’s mission to reach across all platforms and the rise of voice makes up a relevant intersection; voice controlled public radio in Sweden. This thesis has aimed to investigate how radio listeners wish to interact using voice control to listen to on-demand radio content. Additionally, what does public radio need to consider when implementing the UX for voice control? A questionnaire, Google Analytics-data from Sveriges Radio’s mobile app and website, and an interview with National Public Radio were used to determine four initial functions voice controlled on-demand. The functions were turned into four scenarios, used as the basis for a workshop and brainstorming session. Three of these scenarios were then selected to be the foundation for a Wizard of Oz-prototype, which six users evaluated. The results indicate that to create a viable voice user interface (VUI) for radio, there needs to be a profile for the user to create a personalized experience, with filtered searches created by user behaviour and preference settings. The VUI also needs to allow synonyms for program names, as well as keyword tag material for clustering similar material and to enable personalized user searches. This keyword-system can further be utilized to give user recommendations based on behaviour and preferences. A companion application with a graphical user interface (GUI) can be used for such functionality as settings, help, queuing and creating playlists. Finally, the system needs to ensure that the users are taken care of and guided. A radio host can be used as a basis for the system's persona, to create a consistent and familiar interface. Aspects to examine in the future are more extensive user testing for the VUI design, filter bubbles, ensuring that the user data is not misused or leaked, dimensions of the system's persona, the future of radio and the progress of IPAs.

The manufacturing industry has an important role in Sweden's economy and has been producing high quality goods that are exported all over the world for a long time. By using modern technologies such as advanced warehouse systems and digital tools, companies can increase productivity and reduce costs. An example of such modern technology is Automatic Speech Recognition (ASR). Most of the previous research conducted in the field of ASR has focused on analyzing and addressing various kind of problems related to the performance of an ASR-system. Furthermore, there are also a number of studies regarding how ASR has been used in the manufacturing industry, and more specifically, to facilitate order picking. In this work, the use of speech recognition was investigated as a possible method to facilitate and streamline the inventory process. To investigate this, a prototype for a web application has been developed. The application enables a user, through speech recognition, to speech the article number together with the available quantity in the warehouse. Subsequently, the user receives a confirmation both visually and through sound of which the application automatically registers it in the Monitor ERP software. Data has been collected by observing user tests and conducting interviews with indi-viduals who all have some connection to the warehouse at different manufacturing companies. The results indicated that the inventory process could become more ef-fective by using the application. However, some deficiencies were identified during the user tests, which means that the prototype needs further development and increased robustness to be used as a tool during inventory management. / Tillverkningsindustrin är viktig del av Sveriges ekonomi och har under en lång tid producerat högkvalitativa varor som exporteras över hela världen. Genom att använda moderna teknologier som avancerade lagersystem och digitala verktyg, kan företagen öka produktiviteten och minska kostnaderna. Ett exempel på en sådan modern teknologi är Automatic Speech Recognition (ASR). Inom området ASR har en betydande del av den tidigare forskningen ägnats åt att analysera och adressera olika problem relaterade till prestandan hos ett ASR-system. Vidare så finns det även ett antal arbeten kring hur ASR använts inom tillverknings-industrin, och mer specifikt, till att effektivisera orderplockningsprocessen inom in-dustrin. I det här arbetet undersöktes huruvida röststyrning kan användas som ett verktyg för att underlätta samt effektivisera inventeringsprocessen. Detta genomfördes tillsam-mans med företaget Monitor ERP, där en prototyp till en webbapplikation har utvecklats. Prototypen ska med hjälp av röststyrning möjliggöra för en användare att säga artikelnummer samt vilket antal som finns i lagret. Därefter ska användaren få en bekräftelse både visuellt och genom ljud, varav applikationen automatisk registrerar in det till Monitors system. Data har samlats in genom att observera användartester samt utföra intervjuer med personer som alla har någon koppling till lagret på olika tillverkningsföretag. Resultatet visade på att inventeringsprocessen kan bli effektivare genom att utföra inventering med hjälp av applikationen. Däremot upptäcktes en del brister under användartesterna vilket betyder att prototypen behöver utvecklas och bli mer robust för att kunna användas som verktyg under inventering.

The information in the medical records serve many purposes: they can be used for diagnosis and therapy, medical documentation contains information that can be the basis for financial authorities for treatment or for pumping reimbursement from health insurance. The data can be used in statistics and other scientific purposes. The aim of study is to verify the simplicity of data process implementation and time of data storing for modification of classical paper WHO dental card, lifetime dental EHR controlled by keyboard and lifetime dental EHR controlled by voice. All three methods were applied on 126 patients. At first the patients were inspected by a standard technique (communication between dentist and nurse) and the data recorded into the paper WHO dental card. The same person recorded all data to lifetime dental EHR using keyboard and using voice. Then we compared the time, which was needed for recording the data using these three methods. Using Friedman test we found very significant differences in time of recording among three methods (p<0.001). We can see that the paper WHO dental card was recorded quickly, but its rise due to missing electronic form is difficult. Times for recording data using keyboard or voice in lifetime dental EHR were not significantly different. The clinical practice...

The information in the medical records serve many purposes: they can be used for diagnosis and therapy, medical documentation contains information that can be the basis for financial authorities for treatment or for pumping reimbursement from health insurance. The data can be used in statistics and other scientific purposes. The aim of study is to verify the simplicity of data process implementation and time of data storing for modification of classical paper WHO dental card, lifetime dental EHR controlled by keyboard and lifetime dental EHR controlled by voice. All three methods were applied on 126 patients. At first the patients were inspected by a standard technique (communication between dentist and nurse) and the data recorded into the paper WHO dental card. The same person recorded all data to lifetime dental EHR using keyboard and using voice. Then we compared the time, which was needed for recording the data using these three methods. Using Friedman test we found very significant differences in time of recording among three methods (p<0.001). We can see that the paper WHO dental card was recorded quickly, but its rise due to missing electronic form is difficult. Times for recording data using keyboard or voice in lifetime dental EHR were not significantly different. The clinical practice...

Natural language processing is an on-going field that is not yet fully established. A high demand for natural language processing in applications creates a need for good development-tools and different implementation approaches developed to suit the engineers behind the applications. This project approaches the field from an engineering point of view to research approaches, tools, and techniques that are readily available today for development of natural language processing support. The sub-area of information retrieval of natural language processing was examined through a case study, where prototypes were developed to get a deeper understanding of the tools and techniques used for such tasks from an engineering point of view. We found that there are two major approaches to developing natural language processing support for applications, high-level and low-level approaches. A categorization of tools and frameworks belonging to the two approaches as well as the source code, documentation and, evaluations, of two prototypes developed as part of the research are presented. The choice of approach, tools and techniques should be based on the specifications and requirements of the final product and both levels have their own pros and cons. The results of the report are, to a large extent, generalizable as many different natural language processing tasks can be solved using similar solutions even if their goals vary. / Datalingvistik (engelska natural language processing) är ett område inom datavetenskap som ännu inte är fullt etablerat. En hög efterfrågan av stöd för naturligt språk i applikationer skapar ett behov av tillvägagångssätt och verktyg anpassade för ingenjörer. Detta projekt närmar sig området från en ingenjörs synvinkel för att undersöka de tillvägagångssätt, verktyg och tekniker som finns tillgängliga att arbeta med för utveckling av stöd för naturligt språk i applikationer i dagsläget. Delområdet ‘information retrieval’ undersöktes genom en fallstudie, där prototyper utvecklades för att skapa en djupare förståelse av verktygen och teknikerna som används inom området. Vi kom fram till att det går att kategorisera verktyg och tekniker i två olika grupper, beroende på hur distanserad utvecklaren är från den underliggande bearbetningen av språket. Kategorisering av verktyg och tekniker samt källkod, dokumentering och utvärdering av prototyperna presenteras som resultat. Valet av tillvägagångssätt, tekniker och verktyg bör baseras på krav och specifikationer för den färdiga produkten. Resultaten av studien är till stor del generaliserbara eftersom lösningar till många problem inom området är likartade även om de slutgiltiga målen skiljer sig åt.

The aim of the diploma thesis was to create a program with which it will be possible to control a collaborative robot by voice. First chapters contain a search of the current state in the field of collaborative robotics in terms of safety, work efficiency, robot programming and communication with the robot. Furthermore, the issue of machine processing of the human voice is discussed. In practical part was proposed an experiment in which we work with off-line simulation of UR3 robot in PolyScope 3.15.0 software. This simulation was linked to a Python program which uses SpeechRecognition and urx libraries. Simple voice instructions have been designed to move robot to defined position.

Smart home technology develops at a rapid pace and the smart home of today is only a fraction of what the smart home has the potential to become. The ambition of the smart home is to make the everyday life easier for its residents by increasing comfort, safety, and efficiency. As speech recognition accuracy has increased, voice has become an increasingly popular mean of control within the smart home. Both speech recognition and smart home technology have been listed as important emerging technologies for several years with high expected market growth. However, the adoption is slow and one might wonder whether the technologies are failing to diffuse. Though there is an arena for the technologies to work, and benefits to be utilized, the majority of the Swedish population has not adopted the technologies yet. Why is that? This thesis aimed to determine the diffusion prospects of the smart home controlled by voice by investigating; the current consumer adoption rate of the smart home and the smart home controlled by voice; the consumers’ perceptions of smart home technology and voice as a mean of control; and what adoption barriers might hinder the diffusion. To examine this, a literature review of previously identified adoption barriers was conducted, followed by interviews with both technology experts and consumers with different levels of smart home experience. Based on these, initial hypotheses were extracted on consumer perceptions and adoption barriers of smart home technology. These initial hypotheses were subsequently tested by conducting a survey aimed at Swedish families with dependent children. The survey found the adoption of the smart home to have reached half of the Swedish families with dependent children, while the smart home controlled by voice only has been adopted by one-fifth of the families. The smart home technology was found to have good prospects of continuing the diffusion. However, the perceptions of smart home technology vary between consumer groups, where some groups have more difficulties perceiving a purpose with the technology. Voice was further determined unlikely to be the only mean of control of the future smart home, as voice is not found suitable in all situations. This thesis also identified several adoption barriers and problem areas that might hinder the future adoption of smart home technology. Solving these adoption barriers and problems are crucial to increase the diffusion prospects of the smart home. / Tekniken för det smarta hemmet utvecklas i rask takt och den teknik som finns idag är bara en bråkdel av vad det smarta hemmet har potential att utvecklas till. Målet med det smarta hemmet är att förenkla vardagslivet för de som bor i hemmet genom att erbjuda ökad komfort, säkerhet och effektivitet. I takt med att noggrannheten för taligenkänning ökar har röst som kontrollmedel av det smarta hemmet ökat i popularitet. Taligenkänning och tekniken för det smarta hemmet har i flera år listats som viktiga trender och teknikerna förutspås ha hög framtida marknadstillväxt. Adoptionen har emellertid visat sig vara ganska långsam, vilket ger upphov till funderingar kring om teknikerna håller på att misslyckas. Trots att det finns en arena för att teknikerna ska fungera och fördelar att dra nytta av, så har majoriteten av det svenska folket fortfarande inte adopterat teknikerna. Hur kommer sig detta? Det här mastersarbetet ämnar utvärdera framtidsutsikterna för det smarta hemmet kontrollerat av röst. Arbetet undersöker; dagens adoption av det smarta hemmet och det smarta hemmet styrt av röst; konsumenternas uppfattning av tekniken i det smarta hemmet och av röst som kontrollmedel; samt vilka adoptionsbarriärer som skulle kunna hindra diffusionen av teknikerna. En studie av tidigare litteratur i området genomfördes, följt av intervjuer med både teknikexperter och konsumenter med olika erfarenhet av det smarta hemmet. Baserat på litteraturstudien och intervjuerna kunde initiala hypoteser kring konsumenternas uppfattning av teknikerna samt potentiella adoptionsbarriärer extraheras. Dessa hypoteser testades genom en enkätundersökning riktad mot svenska barnfamiljer. Det fastställdes att adoptionen av det smarta hemmet har nått hälften av Sveriges barnfamiljer, medan enbart en femtedel av dessa familjer adopterat det smarta hemmet styrt av röst. Tekniken för det smarta hemmet har goda förutsättningar för fortsatt diffusionen och adoption. Däremot skiljer sig uppfattningarna av tekniken för det smarta hemmet mellan olika konsumentgrupper. Detta då vissa grupper har svårare att uppfatta ett värde med tekniken. Ser man till styrningen av det framtida smarta hemmet är det osannolikt att röst kommer vara det enda styrsättet, eftersom röstkontroll inte är lämpligt i alla situationer. Detta mastersarbete identifierade även flertalet adoptionsbarriärer och problemområden som riskerar hindra teknikens framtida adoption. Dessa är kritiska att lösa för det smarta hemmets framtida diffusion och adoption.

This work investigates the application of active noise control (ANC) to speech. ANC has had success reducing tonal noise. In this work, that success was extended to noise that is not completely tonal but has some tonal elements such as speech. Limitations such as causality were established on the active control of human speech. An optimal configuration for control actuators was developed for a sphere using a genetic algorithm. The optimal error sensor location was found from exploring the nulls associated with the magnitude of the radiated pressure with reference to the primary pressure field. Both numerically predicted and experimentally validated results for the attenuation of single frequency tones were shown. The differences between the numerically predicted results for attenuation with a sphere present in the pressure field and monopoles in the free-field are also discussed.The attenuation from ANC of both monotone and natural speech is shown and a discussion about the effect of causality on the results is given. The sentence “Joe took father’s shoe bench out” was used for both monotone and natural speech. Over this entire monotone speech sentence, the average attenuation was 8.6 dB with a peak attenuation of 10.6 dB for the syllable “Joe”. Natural speech attenuation was 1.1 dB for the sentence average with a peak attenuation on the syllable “bench” of 2.4 dB. In addition to the lower attenuation values for natural speech, the pressure level for the word “took” was increased by 2.3 dB. Also, the harmonic at 420 Hz in the word “father’s” of monotone speech was reduced globally up to 20 dB. Based on the results of the attenuation of monotone and natural speech, it was concluded that a reasonable amount of attenuation could be achieved on natural speech if its correlation could approach that of monotone speech.

Detta arbete har utforskat interaktionen mellan människa och automation inom det avhjälpande underhållet på två tillverkande företag. Arbetets syfte är bidra till att människor och automationsutrustningar framgångsrikt kan samarbeta i framtidens fabriker. Studien har undersökt hur interaktionen ser ut i dagsläget, var det idag saknas interaktion, hur interaktionen kan komma att se ut i framtiden samt vilka krav som behöver uppnås för att komma dit. Studien har också haft ett fokus på hållbar utveckling och hur interaktionen kan påverka denna. Projektets resultat är framtaget genom att utföra två deltagande observationer, en på vartdera företaget samt fyra semistrukturerade intervjuer per företag. I dagsläget sker mycket kommunikation genom telefon för att påkalla uppmärksamhet hos personal med information om larm och plats. Felsökning sker genom en panel vid maskinen alternativt via dator som kopplas upp mot maskinen vid djupare felsökning. Det finns i dagsläget även teknik såsom kommunikationsradio, tangentbord och mus som undviks att användas i största möjliga mån eftersom de anses vara svåra att manövrera. Resultaten visar att det finns ett behov av att få mer information i underhållets alla faser och att tekniken som används behöver vara mer mobil än i dagsläget. Författarna ger förslag på att handhållna enheter kan användas i framtidens underhåll och att röstigenkänning, Virtual Reality och Augmented Reality kan användas i dessa. Även smarta klockor rekommenderas att användas för att påkalla uppmärksamhet hos personal och samtidigt ge information om larm. Det finns en förhoppning om att mer information och mer mobil teknik kan effektivisera underhållet och därmed minska tiden för att utföra ett avhjälpande underhåll. Författarna rekommenderar starkt att all teknik som är tänkt att bli implementerad först testas i en realistisk miljö av de personer som ska använda tekniken. / The project has explored the interaction between humans and automation within the remedial maintenance on two manufacturing companies. The purpose of the project is to contribute to the interaction between humans and automation and by that make it successful in the future. The study has investigated how the present interaction is designed, where there is a need for interaction, how the interaction can be designed in the future together with the requirements that will need to be achieved to get there. In this study there is also a focus on sustainable development and how the interaction affects it. The result of the project is produced by performing two attendance observations, one at each company and four semi-structured interviews at each company. Today a lot of communication is done by phone to get the attention of personnel and summon them to the machine that has stopped. The troubleshooting of the machine is done in a panel or with a computer if deeper troubleshooting is needed. The computer needs to be connected to the machine. Today there are some technics that are present but these are not used due to the fact that they are perceived tedious to use. These technics are communication radio, mouse and keyboard. The result of the study indicates that there is a need for more information in all the phases of a remedial maintenance work. It also shows that the technics needs to be more mobile compared to how it is today. The authors recommends that handheld devices are used in the future and that softwares such as voice recognition, Virtual Reality and Augmented Reality are used within the handheld devices. Smartwatches are also interesting in an attention point of view where alarm messages can be shown. There is a belief that with more information and more mobility the maintenance will be more effective in the future and that the time for remedial maintenance will reduce. The authors strongly recommend that all technics that will be implemented need to first be tested in a realistic environment and by the people that should use it.