Estágio realizado na PT Inovação e orientado pelo Eng.º Sérgio Ramalho / Tese de mestrado integrado. Engenharia Electrotécnica e de Computadores (Major Telecomunicações). Faculdade de Engenharia. Universidade do Porto. 2010

No description available.

Aquesta tesi doctoral mostra la recerca feta en l'àrea de la diarització de locutor per a sales de reunions. En la present s'estudien els algorismes i la implementació d'un sistema en diferit de segmentació i aglomerat de locutor per a grabacions de reunions a on normalment es té accés a més d'un micròfon per al processat. El bloc més important de recerca s'ha fet durant una estada al International Computer Science Institute (ICSI, Berkeley, Caligornia) per un període de dos anys.La diarització de locutor s'ha estudiat força per al domini de grabacions de ràdio i televisió. La majoria dels sistemes proposats utilitzen algun tipus d'aglomerat jeràrquic de les dades en grups acústics a on de bon principi no se sap el número de locutors òptim ni tampoc la seva identitat. Un mètode molt comunment utilitzat s'anomena "bottom-up clustering" (aglomerat de baix-a-dalt), amb el qual inicialment es defineixen molts grups acústics de dades que es van ajuntant de manera iterativa fins a obtenir el nombre òptim de grups tot i acomplint un criteri de parada. Tots aquests sistemes es basen en l'anàlisi d'un canal d'entrada individual, el qual no permet la seva aplicació directa per a reunions. A més a més, molts d'aquests algorisms necessiten entrenar models o afinar els parameters del sistema usant dades externes, el qual dificulta l'aplicabilitat d'aquests sistemes per a dades diferents de les usades per a l'adaptació.La implementació proposada en aquesta tesi es dirigeix a solventar els problemes mencionats anteriorment. Aquesta pren com a punt de partida el sistema existent al ICSI de diarització de locutor basat en l'aglomerat de "baix-a-dalt". Primer es processen els canals de grabació disponibles per a obtindre un sol canal d'audio de qualitat major, a més dínformació sobre la posició dels locutors existents. Aleshores s'implementa un sistema de detecció de veu/silenci que no requereix de cap entrenament previ, i processa els segments de veu resultant amb una versió millorada del sistema mono-canal de diarització de locutor. Aquest sistema ha estat modificat per a l'ús de l'informació de posició dels locutors (quan es tingui) i s'han adaptat i creat nous algorismes per a que el sistema obtingui tanta informació com sigui possible directament del senyal acustic, fent-lo menys depenent de les dades de desenvolupament. El sistema resultant és flexible i es pot usar en qualsevol tipus de sala de reunions pel que fa al nombre de micròfons o la seva posició. El sistema, a més, no requereix en absolute dades d´entrenament, sent més senzill adaptar-lo a diferents tipus de dades o dominis d'aplicació. Finalment, fa un pas endavant en l'ús de parametres que siguin mes robusts als canvis en les dades acústiques. Dos versions del sistema es van presentar amb resultats excel.lents a les evaluacions de RT05s i RT06s del NIST en transcripció rica per a reunions, a on aquests es van avaluar amb dades de dos subdominis diferents (conferencies i reunions). A més a més, es fan experiments utilitzant totes les dades disponibles de les evaluacions RT per a demostrar la viabilitat dels algorisms proposats en aquesta tasca. / This thesis shows research performed into the topic of speaker diarization for meeting rooms. It looks into the algorithms and the implementation of an offline speaker segmentation and clustering system for a meeting recording where usually more than one microphone is available. The main research and system implementation has been done while visiting the International Computes Science Institute (ICSI, Berkeley, California) for a period of two years. Speaker diarization is a well studied topic on the domain of broadcast news recordings. Most of the proposed systems involve some sort of hierarchical clustering of the data into clusters, where the optimum number of speakers of their identities are unknown a priory. A very commonly used method is called bottom-up clustering, where multiple initial clusters are iteratively merged until the optimum number of clusters is reached, according to some stopping criterion. Such systems are based on a single channel input, not allowing a direct application for the meetings domain. Although some efforts have been done to adapt such systems to multichannel data, at the start of this thesis no effective implementation had been proposed. Furthermore, many of these speaker diarization algorithms involve some sort of models training or parameter tuning using external data, which impedes its usability with data different from what they have been adapted to.The implementation proposed in this thesis works towards solving the aforementioned problems. Taking the existing hierarchical bottom-up mono-channel speaker diarization system from ICSI, it first uses a flexible acoustic beamforming to extract speaker location information and obtain a single enhanced signal from all available microphones. It then implements a train-free speech/non-speech detection on such signal and processes the resulting speech segments with an improved version of the mono-channel speaker diarization system. Such system has been modified to use speaker location information (then available) and several algorithms have been adapted or created new to adapt the system behavior to each particular recording by obtaining information directly from the acoustics, making it less dependent on the development data.The resulting system is flexible to any meetings room layout regarding the number of microphones and their placement. It is train-free making it easy to adapt to different sorts of data and domains of application. Finally, it takes a step forward into the use of parameters that are more robust to changes in the acoustic data. Two versions of the system were submitted with excellent results in RT05s and RT06s NIST Rich Transcription evaluations for meetings, where data from two different subdomains (lectures and conferences) was evaluated. Also, experiments using the RT datasets from all meetings evaluations were used to test the different proposed algorithms proving their suitability to the task.

This thesis project is a stand-alone project with the goal to develop an optimized material suited for speaker cabinets, with the focus on acoustic abilities, production possibilities and environmental impact. And to further on design a high performance to price speaker, using the developed material properties and todays technology. The thesis is focused heavily on testing material, starting with research and thereafter creating and testing samples, to continue with find a material combination that would work for a product fit for the market. The final product should fulfill the demands of typical furniture handling, meaning it should be able to be moved around and withstand moderate abuse from daily events. The project results in a functional prototype for evaluation of material and the overall design. The project is based on design methods and design thinking.

A central feature of conversation is that people take it in turns to speak. Typically speaker-listener roles are exchanged in a smooth and orderly fashion, with little or no gap or overlap. To date, within psychology only one comprehensive model of turn-taking has been proposed (Duncan, 1972). This model is cue based and suggests that discrete cues are responsible for the smooth management of conversation. There are, however, a number of fundamental shortcomings in the methodological and conceptual analysis that underpins this model. The aim of this thesis was to address these shortcomings for they have broader implications for our understanding of the turn exchange process. The methodology employed involved both the qualitative and quantitative micro-analysis of conversational data. To test the general significance of this analysis a more experimental approach, involving subjects judgements about particular sections of conversation, was employed. In order to put the generality question to the test, the investigations were based on different types of conversations - face-to-face conversations involving agreement and disagreement and telephone conversations involving travel enquiries and directory enquiries. The research carried out in this thesis has demonstrated that a wider range of information is exploited for turn-taking purposes than previously thought. The turn-taking cues Duncan identified could not provide an adequate explanation of how a smooth exchange of turns was actualised at a particular location. Two judgement studies demonstrated that whilst some conversations were managed by discrete cues as Duncan had suggested, others were not. Further investigations provided evidence that certain aspects of verbal content provide higher order and local information that is important for turn-taking. These investigations thus demonstrated that a cue based model of turn-taking is inadequate and emphasize the need for future work to provide precise explanations about how contextual factors are exploited in this process.

No description available.

No description available.

No description available.

This study was designed to investigate the usefulness of the administration of a Spanish translation of the Peabody Picture Vocabulary Test, Form A, in the language assessment of bilingual children.

No description available.