On the use of spectro-temporal features for the IEEE AASP challenge 'detection and classification of acoustic scenes and events'
نویسندگان
چکیده
In this contribution, an acoustic event detection system based on spectro-temporal features and a two-layer hidden Markov model as back-end is proposed within the framework of the IEEE AASP challenge ‘Detection and Classification of Acoustic Scenes and Events’ (D-CASE). Noise reduction based on the log-spectral amplitude estimator by [1] and noise power density estimation by [2] is used for signal enhancement. Performance based on three different kinds of features is compared, i.e. for amplitude modulation spectrogram, Gabor filterbank-features and conventional Mel-frequency cepstral coefficients (MFCCs), all of them known from automatic speech recognition (ASR). The evaluation is based on the office live recordings provided within the D-CASE challenge. The influence of the signal enhancement is investigated and the increase in recognition rate by the proposed features in comparison to MFCC-features is shown. It is demonstrated that the proposed spectro-temporal features achieve a better recognition accuracy than MFCCs.
منابع مشابه
IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events RECOGNISING ACOUSTIC SCENES WITH LARGE-SCALE AUDIO FEATURE EXTRACTION AND SVM
This work describes our contribution to the IEEE AASP Challenge on classification of acoustic scenes. From the 30 second long highly variable recordings, spectral, cepstral, energy and voicing-related audio features are extracted. A sliding window approach is used to obtain statistical functionals of the low-level features on short segments. SVM are used for classification of these short segmen...
متن کاملIEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events ACOUSTIC EVENT DETECTION USING SIGNAL ENHANCEMENT AND SPECTRO-TEMPORAL FEATURE EXTRACTION
In this paper, an acoustic event detection system is proposed. It consists of a noise reduction signal enhancement step based on the noise power spectral density estimator proposed in [1] and on the noise suppression by [2], a Gabor filterbank feature extraction stage and a two layer hidden Markov model as back-end classifier. Optimization on the development set yields up to a F-Score of 0.73 o...
متن کاملIEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events AN EXEMPLAR-BASED NMF APPROACH FOR AUDIO EVENT DETECTION
We present a novel, exemplar-based method for audio event detection based on non-negative matrix factorisation (NMF). Building on recent work in noise robust automatic speech recognition, we model events as a linear combination of dictionary atoms, and mixtures as a linear combination of overlapping events. The exemplarbased dictionary is created by extracting all available training data, artif...
متن کاملPhoneme Classification Using Temporal Tracking of Speech Clusters in Spectro-temporal Domain
This article presents a new feature extraction technique based on the temporal tracking of clusters in spectro-temporal features space. In the proposed method, auditory cortical outputs were clustered. The attributes of speech clusters were extracted as secondary features. However, the shape and position of speech clusters change during the time. The clusters temporally tracked and temporal tra...
متن کاملWavelets Revisited for the Classification of Acoustic Scenes
We investigate the effectiveness of wavelet features for acoustic scene classification as contribution to the subtask of the IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE2017). On the back-end side, gated recurrent neural networks (GRNNs) are compared against traditional support vector machines (SVMs). We observe that, the proposed wavelet features beh...
متن کامل