Avancerad sökning

Visar resultat 1 - 5 av 83 avhandlingar som matchar ovanstående sökkriterier.

  1. 1. Mining Speech Sounds : Machine Learning Methods for Automatic Speech Recognition and Analysis

    Författare :Giampiero Salvi; Björn Granström; Torbjørn Svendsen; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; speech; machine learning; data mining; signal processing; Computer science; Datavetenskap;

    Sammanfattning : This thesis collects studies on machine learning methods applied to speech technology and speech research problems. The six research papers included in this thesis are organised in three main areas. The first group of studies were carried out within the European project Synface. LÄS MER

  3. 2. Probabilistic Modelling of Hearing : Speech Recognition and Optimal Audiometry

    Författare :Svante Stadler; Arne Leijon; Stefan Stenfelt; KTH; []
    Nyckelord :auditory models; probabilistic modelling; speech modelling; human speech recognition; hearing aids; cochlear implants; psychoacoustics; diagnostic methods; optimal experiments; audiometry;

    Sammanfattning : Hearing loss afflicts as many as 10\% of our population.Fortunately, technologies designed to alleviate the effects ofhearing loss are improving rapidly, including cochlear implantsand the increasing computing power of digital hearing aids. Thisthesis focuses on theoretically sound methods for improvinghearing aid technology. LÄS MER

  4. 3. Information state based speech recognition

    Författare :Rebecca Jonson; Göteborgs universitet; []
    Nyckelord :HUMANIORA; HUMANITIES; dialogue systems; speech recognition; language modelling; dialogue move; dialogue context; ASR; higher level knowledge; linguistic knowledge; N-Best re-ranking; confidence scoring; confidence annotation; information state; ISU approach;

    Sammanfattning : One of the pitfalls in spoken dialogue systems is the brittleness of automatic speech recognition (ASR). ASR systems often misrecognize user input and they are unreliable when it comes to judging their own performance. LÄS MER

  5. 4. Efficient Methods for Automatic Speech Recognition

    Författare :Alexander Seward; KTH; []
    Nyckelord :speech recognition; algorithms; hidden markov models; HMM; weigted finite-state transducers;

    Sammanfattning : This thesis presents work in the area of automatic speech recognition (ASR). The thesis focuses on methods for increasing the efficiency of speech recognition systems and on techniques for efficient representation of different types of knowledge in the decoding process. LÄS MER

  7. 5. Lip-motion biometrics for audio-visual identity recognition

    Författare :Maycel Isaac Faraj; Massimo Tistarelli; Högskolan i Halmstad; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Biometrics; Lip motion; Audio-visual signals; Speech recognition; Speaker recognition; Digit recognition; Image analysis; Bildanalys;

    Sammanfattning : Biometric recognition systems have been established as powerful security tools to prevent unknown users from entering high risk systems and areas. They are increasingly being utilized in surveillance and access management (city centers, banks, etc.) by using individuals' physical or biological characteristics. LÄS MER