Bag of MFCC-based Words for Bird Identification
نویسندگان
چکیده
The algorithm used by the authors in the bird identification task of LifeCLEF 2016 consists in creating a dictionary of MFCC-based words using k-means clustering, computing histograms of these words over short audio segments and feeding them to a random forest classifier. The official score achieved is 0.15 MAP.
منابع مشابه
Multimodal Video Concept Detection via Bag of Auditory Words and Multiple Kernel Learning
State-of-the-art systems for video concept detection mainly rely on visual features. Some previous approaches have also included audio features, either using low-level features such as mel-frequency cepstral coefficients (MFCC) or exploiting the detection of specific audio concepts. In this paper, we investigate a bag of auditory words (BoAW) approach that models MFCC features in an auditory vo...
متن کاملA Content-based Music Similarity Retrieval Scheme by Using BoW Representation and LSH-based Retrieval
This extended abstract paper presents detailed information about a content-based music similarity retrieval scheme, which is based on locality sensitive hashing (LSH). Our scheme considered MFCC and time histogram (TH) as two major features to represent the properties of audio music similarity. Next, each feature is depicted by Bag of Words (BoW), which k-means clustering summarizes extracted f...
متن کاملIdentification of Noisy Speech Signals using Bispectrum-based 2D- MFCC and Its Optimization through Genetic Algorithm as a Feature Extraction Subsystem
Power-spectrum-based Mel-Frequency Cepstrum Coefficients (MFCC) is usually used as a feature extractor in a speaker identification system. This one-dimensional feature extraction subsystem, however, shows low recognition rates for identifying utterance speech signals under harsh noise conditions. In this paper, we have developed a speaker identification system based on Bispectrum data that is m...
متن کاملInstance-based Bird Species Identification with Undiscriminant Features Pruning
This paper reports the participation of Inria to the audiobased bird species identification challenge of LifeCLEF 2014 campaign. Inspired by recent works on fine-grained image classification, we introduce an instance-based classification scheme based on the dense indexing of MFCC features and the pruning of the non-discriminant ones. To make such strategy scalable to the 30M of MFCC features ex...
متن کاملA Bag-of-phonemes Model for Homeplace Classification of Mandarin Speakers
Mandarin, also known as Standard Chinese is the official language of China and Singapore, there are certain differences when mandarin is spoken by people from different homeplaces. The homeplace classification is important in speech recognition and machine translation. In this paper, we proposed a novel model named Bag-of-phonemes (BOP) for homeplace classification of mandarin speakers, which f...
متن کامل