Music Computer & New Media
Topics for Today Characterizing music Identifying music Music recommendation Music summarization Interactive music Composition support Automatic music composition Music management support
Characterizing Music From the audio signal From metadata Beat Brightness Pitch Starting note Potential key (music scale) From metadata Artist Genre(s) Album name, release date On-line ratings/comments Inclusion in playlists Lyrics
Identifying Music Music transcription Query by humming
Music Recommendation For an individual For a playlist For a group Cluster based on features and recommend music similar to what individual likes For a playlist Similar, but add constraints to fill particular amount of time Can also use song-to-song similarity to determine order of music For a group Find music that is most liked, least disliked, or some combination thereof For an activity Use mood or similar information
Music Summarization Most summaries in commercial sites are either the first phrase or a single selected musical phrase Study of whether 22 second long multi-phrase music summaries would be better previews Three algorithms compared that vary the selection of the components between phrases that are sonically distinct and phrases that are repeated more often A comparative evaluation study showed that: Users preferred multi-phrase previews in 87% of the cases over the preview representing the first 22 seconds of the song 90% of all of the multi-phrase summaries were considered at least as good representation of the song as the song’s starting segment
Interactive Music Music games MobiLenin Guitar Hero, Rock Band, … Enable interaction with music in a public space Not karaoke Voting like in many pub/bar games Audience can affect which version of music and video is shown
MobiLenin Interface and Process
Lessons Gave a focal point for interaction between members of a group Content variety is necessary for continued engagement Lottery for free beer motivated participation Well Duh!
Music Composition Support Lots of software tools that help composers generate new works Rapid editing and visualization are common features Some systems provide new models of composition PaperTonnetz
Automatic Music Composition Generation of a musical phrase by learning from examples The Continuator adds phrases in real time using a Markov model based on the artist’s style Example 1 Example 2 Automatic composition of details given higher-level structure of the desired music RapidComposer generates the details given a chord progression
Managing Personal Music Collections Music management is often based on: explicit attributes (e.g. metadata values like the artist, album, and genre). explicit feedback (e.g. ratings of preference and relevance) Benefits Easy to understand Formal: consistent updating and access Context-free Question How can music be accessed based on harder to express personal connections The feelings or memories it triggers? e.g. Music that sounds happy, makes us feel gloomy or reminds us of a person
Current Practices Common metadata tags usually not sufficient to describe mood, feelings, memories, etc. Effort/benefit trade-off Personal reactions change Explicit feedback and usage statistics helpful in retrieving music of preference How would people organize music if there was a low-effort way of expressing their personalized interpretation of music? Use of additional tags or customization of the existing ones can be tedious Use of additional ratings associated to specific music attributes can be overwhelming for the user
Preliminary Study 12 participants asked to organize songs & create playlists in spatial hypertext Visual attributes & spatial layout are changed to express associations The majority found spatial hypertext helpful for organizing Participants appreciated: expressive power and freedom of the workspace directly accessible metadata information of music music previews for remembering music Participants missed: interactive hierarchical / tree views based on metadata music previews for understanding music
Statistics of Artist Similarity Relatedness Assessment MusicWiz Architecture MusicWiz Interface Music management environment that combines: explicit information implicit information non-verbal expression of personal interpretation Two basic components: interface for interacting with the music collection inference engine for assessing music relatedness Metadata Module Audio Signal Module Lyrics Module Worksp. Express. Module Artist Module Relatedness Table Inference Engine Workspace Status Related Song Titles Music Collection Songs & Metadata Songs Lyrics Statistics of Artist Similarity Internet Relatedness Assessment Sim. Values
MusicWiz Interface Hierarchical Folder Tree View Workspace Playlist Pane Related Songs & Search Results View Folder Tree View: Provides a location-based hierarchical views of the music collection. Related Songs & Search Results View: Displays songs that are similar to the currently selected songs in the system tree view or the results of the search. Songs then can be dragged and dropped from the list into the workspace and the playlist pane to update collections and playlists respectively. Playback Controls The MusicWiz interface
MusicWiz Music Similarity Assessment 5 modules for extracting, processing and comparing artists, metadata, audio content, lyrics, and workspace expression Overall Similarity (S1, S2) = = W1 * Overall Metadata Similarity(S1, S2) + + W2 * Overall Audio Signal Similarity(S1, S2) + + W3 * Overall Lyrics Similarity(S1, S2) + + W4 * Overall Workspace Expression Similarity(S1, S2) where, S1, S2 are the songs under comparison and Wn, n = 1..4 the user adjusted weights of the specialized similarity assessments Each module produces an assessment of relatedness (a normalized value ranging from 0 – songs very dissimilar, to 1 – songs almost identical)
MusicWiz Similarity Assessment – Workspace Expression Module Music objects can be related visually and spatially Spatial parser identifies relations between the music objects Recognizes three types of spatial structures: lists, stacks and composites Composite List Stack
MusicWiz Evaluation 20 participants were asked to: Task 1: organize 50 rock songs into sub-collections according to their preference Task 2: form three, twenty-minute long playlists based on three different moods or occasions of their choice Task 3: form three six-song long playlists, where each of them had to be related to a provided “seed”-song (not from the fifty of the original collection)
MusicWiz Evaluation Configuration No Suggestions Suggestions Importance of the workspace Importance of the music previews Four groups of system use: Group 1 (no workspace / no suggestions) had to complete the three tasks using MusicWiz’s browsing, searching, and playback functionality and Windows Explorer folders to form the collections and playlists Group 2 (no workspace / with suggestions) used the same features as group 1 but also received suggestions from the similarity inference engine Group 3 (with workspace / no suggestions) had to perform the tasks using the features available in group 1 but used the MusicWiz workspace to create the collections and playlists Group 4 (with workspace / with suggestions) had all MusicWiz features Configuration No Suggestions Suggestions No Workspace Group 1 Group 2 Workspace Group 3 Group 4
Task 1 - Organization of Music Statement (1 – “I strongly disagree” to 7 – “I strongly agree”) Group 1 Group 2 Group 3 Group 4 The system support in organizing effortlessly / quickly was enough 4.4 5.4 5.6 6.2 Enjoyed doing task 5.8 6.4 6 Organization will be easily understood by others 4.2 Configuration No Suggestions Suggestions No Workspace Group 1 Group 2 Workspace Group 3 Group 4
Tasks 2 & 3 – Playlist Creation Statement (1 – “I strongly disagree” to 7 – “I strongly agree”) Task Group 1 Group 2 Group 3 Group 4 System support for quick selection was enough Two 4.8 6.2 5.8 Three 4.4 6.8 5.6 finding music 6 5.4 4.6 6.4 Enjoyed doing task 5.2 6.6 Configuration No Suggestions Suggestions No Workspace Group 1 Group 2 Workspace Group 3 Group 4
Music Overview Music processing can support a variety of activities Composition From traditional to interactive Selection & Recommendation Example: iTunes, Pandora, Use for shared spaces Playback Example: MobinLenin Management & Summarization Example: MusicWiz Games Guitar Hero, Rockband, etc.