Large-Scale Music Annotation and Retrieval: Learning to Rank in Joint Semantic Spaces

نویسندگان

  • Jason Weston
  • Samy Bengio
  • Philippe Hamel
چکیده

Music prediction tasks range from predicting tags given a song or clip of audio, predicting the name of the artist, or predicting related songs given a song, clip, artist name or tag. That is, we are interested in every semantic relationship between the different musical concepts in our database. In realistically sized databases, the number of songs is measured in the hundreds of thousands or more, and the number of artists in the tens of thousands or more, providing a considerable challenge to standard machine learning techniques. In this work, we propose a method that scales to such datasets which attempts to capture the semantic similarities between the database items by modeling audio, artist names, and tags in a single low-dimensional semantic space. This choice of space is learnt by optimizing the set of prediction tasks of interest jointly using multi-task learning. Our method both outperforms baseline methods and, in comparison to them, is faster and consumes less memory. We then demonstrate how our method learns an interpretable model, where the semantic space captures well the similarities of interest.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Multi-Tasking with Joint Semantic Spaces for Large-Scale Music Annotation and Retrieval

Music prediction tasks range from predicting tags given a song or clip of audio, predicting the name of the artist, or predicting related songs given a song, clip, artist name or tag. That is, we are interested in every semantic relationship between the different musical concepts in our database. In realistically sized databases, the number of songs is measured in the hundreds of thousands or m...

متن کامل

Heuristic Label Set Relevance Learning for Image Annotation

Automatic annotation can automatically annotate images with semantic labels to significantly facilitate image retrieval and organization. Traditional web image annotation methods often estimate specific label relevance to image, and neglect the relevance of the assigned label set as a whole. In this paper, A novel image annotation method by heuristic relevance learning is proposed. Label releva...

متن کامل

Online Learning to Rank for Content-Based Image Retrieval

A major challenge in Content-Based Image Retrieval (CBIR) is to bridge the semantic gap between low-level image contents and high-level semantic concepts. Although researchers have investigated a variety of retrieval techniques using different types of features and distance functions, no single best retrieval solution can fully tackle this challenge. In a real-world CBIR task, it is often highl...

متن کامل

Music Warehouses: Challenges for the Next Generation of Music Search Engines

Music Information Retrieval has received increasing attention from both the industrial and the research communities in recent years. Many audio extraction techniques providing content-based music information have been developed, sparking the need for intelligent storage and retrieval facilities. This paper proposes to satisfy this need by extending technology from business-oriented data warehou...

متن کامل

Exploring the Semantic Annotation and Retrieval of Sound

We present a computer audition system that can both annotate novel audio tracks with semantically meaningful words and use a semantic query to retrieve relevant tracks from database of unlabeled audio content. We consider the related tasks of content-based audio annotation and retrieval as one supervised multi-class problem in which we model the joint probability of acoustic features and words....

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • CoRR

دوره abs/1105.5196  شماره 

صفحات  -

تاریخ انتشار 2011