Noise-robust HMM-based pattern recognition using multimodal features and observation uncertainties
نویسنده
چکیده
Im Bereich der automatischen Spracherkennung (ASR) sind eine Reihe von sogenannten beobachtungsunsicherheitsbasierten Decodierungsansätze vorgeschlagen worden, um die notwendige Robustheit zu erzielen. Die Grundidee dieser Ansätze ist, dass die Fehlanpassung zwischen den gestörten akustischen Beobachtungen und dem zugrundeliegenden statistischen Modell dadurch kompensiert wird, dass die beobachteten verzerrten akustischen Daten nicht als deterministisch sondern als Zufallsvariablen mit einem zeitlich variierenden Unsicherheitsgrad betrachtet werden. Je größer die Unsicherheit eines bestimmten akustischen Merkmals ist, desto kleiner wird ihr Beitrag zur Erkennung.
منابع مشابه
MAN-MACHINE INTERACTION SYSTEM FOR SUBJECT INDEPENDENT SIGN LANGUAGE RECOGNITION USING FUZZY HIDDEN MARKOV MODEL
Sign language recognition has spawned more and more interest in human–computer interaction society. The major challenge that SLR recognition faces now is developing methods that will scale well with increasing vocabulary size with a limited set of training data for the signer independent application. The automatic SLR based on hidden Markov models (HMMs) is very sensitive to gesture's shape inf...
متن کاملA New Fast and Efficient HMM-Based Face Recognition System Using a 7-State HMM Along With SVD Coefficients
In this paper, a new Hidden Markov Model (HMM)-based face recognition system is proposed. As a novel point despite of five-state HMM used in pervious researches, we used 7-state HMM to cover more details. Indeed we add two new face regions, eyebrows and chin, to the model. As another novel point, we used a small number of quantized Singular Values Decomposition (SVD) coefficients as feature...
متن کاملA new posterior based audio-visual integration method for robust speech recognition
We describe the development of a multistream HMM based audio-visual speech recognition (AVSR) system and a new method for integrating the audio and visual streams using frame level posterior probabilities. This is compared to the standard feature concatenation and weighted product methods in speaker-dependent tests using our own multimodal database, by examining speech recognition robustness to...
متن کاملA Hybrid HMM/BN Acoustic Model for Automatic Speech Recognition
In current HMM based speech recognition systems, it is difficult to supplement acoustic spectrum features with additional information such as pitch, gender, articulator positions, etc. On the other hand, Bayesian Networks (BN) allow for easy combination of different continuous as well as discrete features by exploring conditional dependencies between them. However, the lack of efficient algorit...
متن کاملModeling Hmm State Distributions
In current HMM based speech recognition systems, it is difficult to supplement acoustic spectrum features with additional information such as pitch, gender, articulator positions, etc. On the other hand, Bayesian Networks (BN) allow for easy combination of different continuous as well as discrete features by exploring conditional dependencies between them. However, the lack of efficient algorit...
متن کامل