Music score alignment and computer accompaniment

Dannenberg, Roger B.; Raphael, Christopher

doi:10.1145/1145287.1145311

Cited by 72 publications

(44 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The unbiased estimate of the standard deviation of accuracy over songs is (3) which provides a measure of the variation of accuracy between songs. The mean absolute deviation th (4) between the time instant at beginning of the th target word and its estimate (also averaged over all songs) allows an additional approach to the results. The metrics and are illustrated in Fig.…”

Section: Results Imentioning

confidence: 99%

“…The reason is that VAD allows the occurrence of a word only in regions identified as "vocal': VAD achieves an improvement when no coarse alignment via chords is available, even though some sections may be falsely classified as non-vocal. However, when additional chord information is used, it also provides this coarse alignment and VAD becomes obsolete; regions erroneously detected as non-vocal 4 will then decrease results.…”

Section: Influence Of Parameters When Both Audio Features Are Presentmentioning

confidence: 99%

See 1 more Smart Citation

Integrating Additional Chord Information Into HMM-Based Lyrics-to-Audio Alignment

Mauch

Fujihara

Goto

2012

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-Aligning lyrics to audio has a wide range of applications such as the automatic generation of karaoke scores, song-browsing by lyrics, and the generation of audio thumbnails. Existing methods are restricted to using only lyrics and match them to phoneme features extracted from the audio (usually mel-frequency cepstral coefficients). Our novel idea is to integrate the textual chord information provided in the paired chords-lyrics format known from song books and Internet sites into the inference procedure. We propose two novel methods that implement this idea: First, assuming that all chords of a song are known, we extend a hidden Markov model (HMM) framework by including chord changes in the Markov chain and an additional audio feature (chroma) in the emission vector; second, for the more realistic case in which some chord information is missing, we present a method that recovers the missing chord information by exploiting repetition in the song. We conducted experiments with five changing parameters and show that with accuracies of 87.5% and 76.7%, respectively, both methods perform better than the baseline with statistical significance. We introduce the new accompaniment interface Song Prompter, which uses the automatically aligned lyrics to guide musicians through a song. It demonstrates that the automatic alignment is accurate enough to be used in a musical performance.Index Terms-Audio user interfaces, hidden Markov models (HMMs), music, music information retrieval, speech processing.

show abstract

Section: Results Imentioning

confidence: 99%

Section: Influence Of Parameters When Both Audio Features Are Presentmentioning

confidence: 99%

Integrating Additional Chord Information Into HMM-Based Lyrics-to-Audio Alignment

Mauch

Fujihara

Goto

2012

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…For richer musical interaction, the robot should allow for the pitch information in the human's performance. Audio to score alignment [12] is promising technique to achieve a pitch-based musical ensemble. Second, the ensemble with multiple humans is a challenging task because the synchronization becomes even harder when all members try to adapt to another member.…”

Section: Resultsmentioning

confidence: 99%

Music-Ensemble Robot That Is Capable of Playing the Theremin While Listening to the Accompanied Music

Otsuka¹,

Mizumoto²,

Nakadai³

et al. 2010

Trends in Applied Intelligent Systems

View full text Add to dashboard Cite

Abstract. Our goal is to achieve a musical ensemble among a robot and human musicians where the robot listens to the music with its own microphones. The main issues are (1) robust beat-tracking since the robot hears its own generated sounds in addition to the accompanied music, and (2) robust synchronizing its performance with the accompanied music even if humans' musical performance fluctuates. This paper presents a music-ensemble Thereminist robot implemented on the humanoid HRP-2 with the following three functions: (1) self-generated Theremin sound suppression by semi-blind Independent Component Analysis, (2) beat tracking robust against tempo fluctuation in humans' performance, and (3) feedforward control of Theremin pitch. Experimental results with a human drummer show the capability of this robot for the adaptation to the temporal fluctuation in his performance.

show abstract

“…Furthermore, alignment problems as discussed in this paper are closely related to tasks such as automated accompaniment [20], [21] and score following [22]. However, alignment strategies often employed in these fields such as hidden Markov models (HMMs) [23] and other graphical models [24], [25] are not further considered in the following.…”

Section: F Concluding Remarksmentioning

confidence: 99%

Towards Cross-Version Harmonic Analysis of Music

Ewert

Müller

Konz

et al. 2012

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Abstract-For a given piece of music, there often exist multiple versions belonging to the symbolic (e.g., MIDI representations), acoustic (audio recordings), or visual (sheet music) domain. Each type of information allows for applying specialized, domain-specific approaches to music analysis tasks. In this paper, we formulate the idea of a cross-version analysis for comparing and/or combining analysis results from different representations. As an example, we realize this idea in the context of harmonic analysis to automatically evaluate MIDI-based chord labeling procedures using annotations given for corresponding audio recordings. To this end, one needs reliable synchronization procedures that automatically establish the musical relationship between the multiple versions of a given piece. This becomes a hard problem when there are significant local deviations in these versions. We introduce a novel late-fusion approach that combines different alignment procedures in order to identify reliable parts in synchronization results. Then, the cross-version comparison of the various chord labeling results is performed only on the basis of the reliable parts. Finally, we show how inconsistencies in these results across the different versions allow for a quantitative and qualitative evaluation, which not only indicates limitations of the employed chord labeling strategies but also deepens the understanding of the underlying music material.

show abstract

Music score alignment and computer accompaniment

Abstract: By relating musical sound to musical notation, these systems generate tireless, expressive musical accompaniment to follow and sometimes learn from a live human performance.

Cited by 72 publications

References 5 publications

Integrating Additional Chord Information Into HMM-Based Lyrics-to-Audio Alignment

Integrating Additional Chord Information Into HMM-Based Lyrics-to-Audio Alignment

Music-Ensemble Robot That Is Capable of Playing the Theremin While Listening to the Accompanied Music

Towards Cross-Version Harmonic Analysis of Music

Contact Info

Product

Resources

About