Timbral modeling for music artist recognition using i-vectors

Eghbal-zadeh, Hamid; Schedl, Markus; Widmer, Gerhard

doi:10.1109/eusipco.2015.7362591

Cited by 14 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The exploited audio features are inspired by the fields of speech processing and music information retrieval (MIR) and by their successful application in MIR-related tasks, including music retrieval, music classification, and music recommendation (Knees and Schedl 2016). We investigate two kinds of audio features: (i) block-level features (Seyerlehner et al 2011) which consider chunks of the audio signal known as blocks and are therefore capable of exploiting temporal aspects of the signal; and (ii) i-vector features (Eghbal-Zadeh et al 2015) which are extracted at the level of audio segments using audio frames. Both approaches eventually model the feature at the level of the entire audio piece; by aggregating the individual feature vectors across time.…”

Section: Audio Featuresmentioning

confidence: 99%

“…The framework can be decomposed into several stages: (i) Frame-level feature extraction MFCCs have proven to be useful features for many audio and music processing tasks (Logan et al 2000b;Ellis 2007;Eghbal-Zadeh et al 2015). They provide a compact representation of the spectral envelope are also a musically meaningful representation (Eghbal-Zadeh et al 2015), and are used to capture acoustic scenes (Eghbal-Zadeh et al 2016). Even though it is possible to use other features (Suh et al 2011), we avoid the challenges involved in feature engineering and instead focus on the timbral modeling technique.…”

Section: Block-level Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Movie genome: alleviating new item cold start in movie recommendation

Deldjoo

Dacrema

Constantin

et al. 2019

User Model User-Adap Inter

Self Cite

View full text Add to dashboard Cite

As of today, most movie recommendation services base their recommendations on collaborative filtering (CF) and/or content-based filtering (CBF) models that use metadata (e.g., genre or cast). In most video-on-demand and streaming services, however, new movies and TV series are continuously added. CF models are unable to make predictions in such a scenario, since the newly added videos lack interactions-a problem technically known as new item cold start (CS). Currently, the most common approach to this problem is to switch to a purely CBF method, usually by exploiting textual metadata. This approach is known to have lower accuracy than CF because it ignores useful collaborative information and relies on human-generated textual metadata, which are expensive to collect and often prone to errors. User-generated content, such as tags, can also be rare or absent in CS situations. In this paper, we introduce a new movie recommender system that addresses the new item problem in the movie domain by (i) integrating state-of-the-art audio and visual descriptors, which can be automatically extracted from video content and constitute what we call the movie genome; (ii) exploiting an effective data fusion method named canonical correlation analysis, which was successfully tested in our previous works Deldjoo et alto better exploit complementary information between different modalities; (iii) proposing a two-step hybrid approach which trains a CF model on warm items (items with interactions) and leverages the learned model on the movie genome to recommend cold items (items without interactions). Experimental validation is carried out using a system-centric study on a large-scale, real-world movie recommendation dataset both in an absolute cold start and in a cold to warm transition; and a user-centric online experiment measuring different subjective aspects, such as satisfaction and diversity. Results show the benefits of this approach compared to existing approaches.

show abstract

Section: Audio Featuresmentioning

confidence: 99%

Section: Block-level Featuresmentioning

confidence: 99%

Movie genome: alleviating new item cold start in movie recommendation

Deldjoo

Dacrema

Constantin

et al. 2019

User Model User-Adap Inter

Self Cite

View full text Add to dashboard Cite

show abstract

“…Studies have mostly focused on feature extraction methods, which extract a singer's voice from an audio signal. The extracted features include Mel-frequency cepstral coefficient (MFCC) features [3]- [5], linear frequency cepstral coefficient features [6], [7], harmonic features [6], cepstrum-based features [8], GMM super-vectors [9], and i-vectors [10], [12]. Segmenting a singer's voice and musical instrument is itself a classification problem and is outside the scope of this study.…”

Section: Background and Related Workmentioning

confidence: 99%

Hidden Singer: Distinguishing Imitation Singers Based on Training with Only the Original Song

Park

Nam

Choi

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Hidden Singer is a television program in Korea. In the show, the original singer and four imitating singers sing a song in hiding behind a screen. The audience and TV viewers attempt to guess who the original singer is by listening to the singing voices. Usually, there are few correct answers from the audience, because the imitators are well trained and highly skilled. We propose a computerized system for distinguishing the original singer from the imitating singers. During the training phase, the system learns only the original singer's song because it is the one the audience has heard before. During the testing phase, the songs of five candidates are provided to the system and the system then determines the original singer. The system uses a 1-class authentication method, in which only a subject model is made. The subject model is used for measuring similarities between the candidate songs. In this problem, unlike other existing studies that require artist identification, we cannot utilize multi-class classifiers and supervised learning because songs of the imitators and the labels are not provided during the training phase. Therefore, we evaluate the performances of several 1-class learning algorithms to choose which one is more efficient in distinguishing an original singer from among highly skilled imitators. The experiment results show that the proposed system using the autoencoder performs better (63.33%) than other 1-class learning algorithms: Gaussian mixture model (GMM) (50%) and one class support vector machines (OCSVM) (26.67%). We also conduct a human contest to compare the performance of the proposed system with human perception. The accuracy of the proposed system is found to be better (63.33%) than the average accuracy of human perception (33.48%).

show abstract

“…Features. I-vectors were first introduced in the field of speaker verification [10], but recently they have also been successfully utilized for music similarity and music artist recognition tasks [12,13]. We build a Gaussian mixture model with 1,024 components on the entire pool of segment-level features of the development song set.…”

Section: I-vectors From Timbralmentioning

confidence: 99%

Proceedings of the 33rd Annual ACM Symposium on Applied Computing

Roosmalen¹,

Vranken

Eekelen

2018

View full text Add to dashboard Cite

Automated music playlist continuation is a common task of music recommender systems, that generally consists in providing a fitting extension to a given playlist. Collaborative filtering models, that extract abstract patterns from curated music playlists, tend to provide better playlist continuations than content-based approaches. However, pure collaborative filtering models have at least one of the following limitations: (1) they can only extend playlists profiled at training time; (2) they misrepresent songs that occur in very few playlists. We introduce a novel hybrid playlist continuation model based on what we name "playlist-song membership, " that is, whether a given playlist and a given song fit together. The proposed model regards any playlist-song pair exclusively in terms of feature vectors. In light of this information, and after having been trained on a collection of labeled playlist-song pairs, the proposed model decides whether a playlist-song pair fits together or not. Experimental results on two datasets of curated music playlists show that the proposed playlist continuation model compares to a state-of-theart collaborative filtering model in the ideal situation of extending playlists profiled at training time and where songs occurred frequently in training playlists. In contrast to the collaborative filtering model, and as a result of its general understanding of the playlistsong pairs in terms of feature vectors, the proposed model is additionally able to (1) extend non-profiled playlists and (2) recommend songs that occurred seldom or never in training playlists. CCS CONCEPTS• Information systems → Recommender systems; KEYWORDS automated music playlist continuation, hybrid recommender systems, music information retrieval, neural networks ACM Reference Format:

show abstract

Timbral modeling for music artist recognition using i-vectors

Cited by 14 publications

References 14 publications

Movie genome: alleviating new item cold start in movie recommendation

Movie genome: alleviating new item cold start in movie recommendation

Hidden Singer: Distinguishing Imitation Singers Based on Training with Only the Original Song

Proceedings of the 33rd Annual ACM Symposium on Applied Computing

Contact Info

Product

Resources

About