Sökning: "speech recognition"

Visar resultat 21 - 25 av 83 avhandlingar innehållade orden speech recognition.

  1. 21. Recognition and Generation of Communicative Signals : Modeling of Hand Gestures, Speech Activity and Eye-Gaze in Human-Machine Interaction

    Författare :Kalin Stefanov; Jonas Beskow; Gerasimos Potamianos; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES;

    Sammanfattning : Nonverbal communication is essential for natural and effective face-to-face human-human interaction. It is the process of communicating through sending and receiving wordless (mostly visual, but also auditory) signals between people. Consequently, a natural and effective face-to-face human-machine interaction requires machines (e.g. LÄS MER

  3. 22. Accounting for Individual Speaker Properties in Automatic Speech Recognition

    Författare :Daniel Elenius; Björn Granström; Mats Blomberg; Torjbjörn Svendsen; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; MAP; MLLR; VTLN; speaker characteristics; dynamic modeling; child; Information and language technology; Informations- och språkteknologi;

    Sammanfattning : In this work, speaker characteristic modeling has been applied in the fields of automatic speech recognition (ASR) and automatic speaker verification (ASV). In ASR, a key problem is that acoustic mismatch between training and test conditions degrade classification per- formance. LÄS MER

  4. 23. Hearing and cognition in speech comprehension. Methods and applications

    Författare :Mathias Hällgren; Stig Arlinger; Birgitta Larsby; Arne Leijon; Linköpings universitet; []
    Nyckelord :MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; Aging; physiology; cognition; cognition disorders; dichotic listening tests; hearing loss; sensorineural; neuropsychological tests; speech perception; Audiology; Audiologi;

    Sammanfattning : Central auditory processing is complex and can not be evaluated by a single method. This thesis focuses on assessment of some aspects of central auditory functions by the use of dichotic speech tests and cognitive tests that tax functions important for speech processing. LÄS MER

  5. 24. Speech Enhancement Using Nonnegative MatrixFactorization and Hidden Markov Models

    Författare :Nasser Mohammadiha; Arne Leijon; W. Bastiaan Kleijn; Cédric Févotte; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Speech enhancement; noise reduction; nonnegative matrix factorization; hidden Markov model; probabilistic latent component analysis; online dictionary learning; super-Gaussian distribution; MMSE estimator; temporal dependencies; dynamic NMF;

    Sammanfattning : Reducing interference noise in a noisy speech recording has been a challenging task for many years yet has a variety of applications, for example, in handsfree mobile communications, in speech recognition, and in hearing aids. Traditional single-channel noise reduction schemes, such as Wiener filtering, do not work satisfactorily in the presence of non-stationary background noise. LÄS MER

  7. 25. Subband Beamforming for Speech Enhancement in Hands-Free Communication

    Författare :Zohra Yermeche; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Beamforming; Speech enhancement; Subband filtering;

    Sammanfattning : Speech enhancement by means of microphone array signal processing has a major role in voice communication applications such as audio-conferencing, hands-free telephony, voice recognition and hearing aids. In these communication scenarios, the speaker is positioned at a remote distance from the microphones, which causes problems of environment noise and interfering sound corrupting the received speech. LÄS MER