Speaker, Noise, and Acoustic Space Adaptation for Emotion Recognition in the Automotive Environment
نویسنده
چکیده
Emotional surveillance of drivers possesses significant potential for increased security within passenger transport. In an automotive setting the interaction can further be improved by social awareness of an MMI. Within this scope the detection of security relevant behavior patterns as aggressiveness or sadness is discussed. The focus lies on real-life usage respecting online processing, subject independency, and noise robustness. The approach introduced employs multivariate time-series analysis by brute-force feature generation. Extensive results are reported on two public standard corpora. The influence of noise is discussed by representative car-noise overlay. Thereby impact per low-level-descriptor is considered.
منابع مشابه
Acoustic Emotion Recognition in Car Environment Using a 3D Emotion Space Approach
Introduction The automatic assessment of emotions conveyed in the speech signal has become a rapidly growing research interest in recent years. This paper focuses on a generalized framework to estimate emotions from the speech using an emotion space concept. The performance of such a system is studied in the acoustically demanding environment of vehicular noise while driving. Due to the increas...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملEffects of In-Car Noise-Conditions on the Recognition of Emotion within Speech
Integration of affective cues is considered a major factor towards future human-machine communication with respect to more naturalness. Today’s in-car interfaces are already enhanced by speech recognition. In this contribution we therefore investigate the effects of acoustic in-car conditions on the recognition of emotion within speech, as it may be highly susceptible to noise [3]. Diverse driv...
متن کاملMultichannel-Noise Reduction-Systems for Speaker Identification in an Automotive Environment
Devices for communication and information utilised by car drivers are facing two essential requirements: hands-free operation via distant microphones but also robustness against different noises depending on car speed etc. Automatic speaker identification can be utilized within such devices to either supply speech recognition systems with so called apriori information to achieve higher recognit...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کامل