We propose a system to adapt a user’s music to their exercise by aligning high-energy music segments with intense intervals of the workout. Listening to music during exercise can boost motivation and performance. However, the structure of the music may be different from the user’s natural phases of rest and work, causing users to rest longer than needed while waiting for a motivational section, or lose motivation mid-work if the section ends too soon. To address this, our system, called RISE, automatically estimates the intense segments in music and uses cutpoint-based music rearrangement techniques to dynamically extend and shorten different segments of the user’s song to fit the ongoing exercise routine. Our system takes as input the rest and work durations to guide adaptation. Currently, this is determined either via a pre-defined plan or manual input during the workout. We evaluated RISE with 12 participants who compared our system to a non-adaptive music baseline while exercising in our lab. Participants found our rearrangements seamless, intensity estimation accurate, and many recalled moments when intensity alignment helped them push through their workout.

Q2 ( I am an expert on the topic of the paper.)

Agree

Q3 ( The title and abstract reflect the content of the paper.)

Strongly disagree

Q4 (The paper discusses, cites and compares with all relevant related work.)

Agree

Q6 (Readability and paper organization: The writing and language are clear and structured in a logical manner.)

Strongly agree

Q7 (The paper adheres to ISMIR 2025 submission guidelines (uses the ISMIR 2025 template, has at most 6 pages of technical content followed by “n” pages of references or ethical considerations, references are well formatted). If you selected “No”, please explain the issue in your comments.)

Yes

Q8 (Relevance of the topic to ISMIR: The topic of the paper is relevant to the ISMIR community. Note that submissions of novel music-related topics, tasks, and applications are highly encouraged. If you think that the paper has merit but does not exactly match the topics of ISMIR, please do not simply reject the paper but instead communicate this to the Program Committee Chairs. Please do not penalize the paper when the proposed method can also be applied to non-music domains if it is shown to be useful in music domains.)

Strongly agree

Q9 (Scholarly/scientific quality: The content is scientifically correct.)

Strongly agree

Q11 (Novelty of the paper: The paper provides novel methods, applications, findings or results. Please do not narrowly view "novelty" as only new methods or theories. Papers proposing novel musical applications of existing methods from other research fields are considered novel at ISMIR conferences.)

Agree

Q12 (The paper provides all the necessary details or material to reproduce the results described in the paper. Keep in mind that ISMIR respects the diversity of academic disciplines, backgrounds, and approaches. Although ISMIR has a tradition of publishing open datasets and open-source projects to enhance the scientific reproducibility, ISMIR accepts submissions using proprietary datasets and implementations that are not sharable. Please do not simply reject the paper when proprietary datasets or implementations are used.)

Agree

Q13 (Pioneering proposals: This paper proposes a novel topic, task or application. Since this is intended to encourage brave new ideas and challenges, papers rated “Strongly Agree” and “Agree” can be highlighted, but please do not penalize papers rated “Disagree” or “Strongly Disagree”. Keep in mind that it is often difficult to provide baseline comparisons for novel topics, tasks, or applications. If you think that the novelty is high but the evaluation is weak, please do not simply reject the paper but carefully assess the value of the paper for the community.)

Agree (Novel topic, task, or application)

Q14 (Reusable insights: The paper provides reusable insights (i.e. the capacity to gain an accurate and deep understanding). Such insights may go beyond the scope of the paper, domain or application, in order to build up consistent knowledge across the MIR community.)

Strongly agree

Q15 (Please explain your assessment of reusable insights in the paper.)

This paper clearly presents a novel approach for adaptively controlling playback of existing music audio to better match the burst and rest phases of workouts, and discusses its effectiveness and limitations based on a user study with 12 participants.

Q16 ( Write ONE line (in your own words) with the main take-home message from the paper.)

This paper proposes a system that loops or skips parts of music to align its high-energy segments with workout bursts and its low-energy segments with rest periods.

Q17 (This paper is of award-winning quality.)

No

Q19 (Potential to generate discourse: The paper will generate discourse at the ISMIR conference or have a large influence/impact on the future of the ISMIR community.)

Strongly agree

Q20 (Overall evaluation (to be completed before the discussion phase): Please first evaluate before the discussion phase. Keep in mind that minor flaws can be corrected, and should not be a reason to reject a paper. Please familiarize yourself with the reviewer guidelines at https://ismir.net/reviewer-guidelines.)

Strong accept

Q21 (Main review and comments for the authors (to be completed before the discussion phase). Please summarize strengths and weaknesses of the paper. It is essential that you justify the reason for the overall evaluation score in detail. Keep in mind that belittling or sarcastic comments are not appropriate.)

This paper describes a novel system that loops and skips existing music audio to better suit exercise activities. The paper is very well-written and makes clear contributions. Given the following strengths, I recommend "Strong accept."

• The processing steps in the system are well-justified and highly regarded. The system first obtains structural segments and beats using an existing method and classifies each segment as either a high-intensity or low-intensity segment by computing beat-level LUFS loudness. Although the binary labeling of segments is a simple approach, it effectively serves the intended purpose. It then estimates intra-segment cuepoints using a beat-level self-similarity matrix to achieve natural looping and skipping. Limiting jumps to within segments enhances the naturalness of transitions and is a reasonable design choice. Finally, music playback is adaptively looped or skipped in two ways: either by following a predefined workout plan of burst and rest phases or by adjusting playback in real time through manual button controls when transitioning between phases. Although relying on manual controls is a limitation and ideally the system should sense the user's physical state and make automatic decisions, the authors explicitly acknowledge this limitation in Section 6.

• The user study with 12 participants clearly demonstrates the system's effectiveness through analysis of interview transcripts. Participants who were initially skeptical about the naturalness of looping and skipping audio before the experiment came to appreciate its effectiveness after experiencing it firsthand. In addition, participants reported that the adaptive playback "helped them push through and get an extra one or two reps," which shows the practical benefits of the proposed system.

[Suggested improvements]

• The word "Rearrangement" in the title is misleading, as it typically refers to changes in instrumentation or harmony. Since this system only performs adaptive playback control without modifying the music audio itself, I strongly recommend rephrasing the title.

• There is a typo in reference [19]: "2006, p. 7th." I suggest carefully reviewing the references again.

Q22 (Final recommendation (to be completed after the discussion phase) Please give a final recommendation after the discussion phase. In the final recommendation, please do not simply average the scores of the reviewers. Note that the number of recommendation options for reviewers is different from the number of options here. We encourage you to take a stand, and preferably avoid “weak accepts” or “weak rejects” if possible.)

Weak accept

Q23 (Meta-review and final comments for authors (to be completed after the discussion phase))

This paper has several strengths, such as "This work presents a timely and compelling contribution" (R4), "The methodological rigor is commendable" (R4), "The concept is promising" (R5), "This is an interesting topic and application for the MIR research." (R7), and "a novel system that loops and skips existing music audio to better suit exercise activities" (meta-reviewer).

However, as pointed out by the reviewers, there are several weaknesses that should be addressed through revision. In particular, the need for manual input to identify 'high' and 'low' intensity segments should be clearly emphasized much earlier in the paper. Furthermore, as noted in the review comments, the title is misleading and should be revised to better reflect the content of the paper.

Since all reviewers gave positive ratings (two "Strong accept" and two "Weak accept"), an "Accept" recommendation was considered. However, based on the comments regarding the weaknesses, it was suggested during the discussion phase that the final recommendation should be "Weak accept." Therefore, our final recommendation is "Weak accept", though it is close to an "Accept" assuming that the identified issues will be thoroughly addressed. If this paper is accepted, the authors are strongly expected to address the issues raised in the reviews.

Q2 ( I am an expert on the topic of the paper.)

Agree

Q3 (The title and abstract reflect the content of the paper.)

Agree

Q4 (The paper discusses, cites and compares with all relevant related work)

Agree

Q6 (Readability and paper organization: The writing and language are clear and structured in a logical manner.)

Agree

Q7 (The paper adheres to ISMIR 2025 submission guidelines (uses the ISMIR 2025 template, has at most 6 pages of technical content followed by “n” pages of references or ethical considerations, references are well formatted). If you selected “No”, please explain the issue in your comments.)

Yes

Q8 (Relevance of the topic to ISMIR: The topic of the paper is relevant to the ISMIR community. Note that submissions of novel music-related topics, tasks, and applications are highly encouraged. If you think that the paper has merit but does not exactly match the topics of ISMIR, please do not simply reject the paper but instead communicate this to the Program Committee Chairs. Please do not penalize the paper when the proposed method can also be applied to non-music domains if it is shown to be useful in music domains.)

Agree

Q9 (Scholarly/scientific quality: The content is scientifically correct.)

Agree

Q11 (Novelty of the paper: The paper provides novel methods, applications, findings or results. Please do not narrowly view "novelty" as only new methods or theories. Papers proposing novel musical applications of existing methods from other research fields are considered novel at ISMIR conferences.)

Agree

Q12 (The paper provides all the necessary details or material to reproduce the results described in the paper. Keep in mind that ISMIR respects the diversity of academic disciplines, backgrounds, and approaches. Although ISMIR has a tradition of publishing open datasets and open-source projects to enhance the scientific reproducibility, ISMIR accepts submissions using proprietary datasets and implementations that are not sharable. Please do not simply reject the paper when proprietary datasets or implementations are used.)

Agree

Q13 (Pioneering proposals: This paper proposes a novel topic, task or application. Since this is intended to encourage brave new ideas and challenges, papers rated "Strongly Agree" and "Agree" can be highlighted, but please do not penalize papers rated "Disagree" or "Strongly Disagree". Keep in mind that it is often difficult to provide baseline comparisons for novel topics, tasks, or applications. If you think that the novelty is high but the evaluation is weak, please do not simply reject the paper but carefully assess the value of the paper for the community.)

Agree (Novel topic, task, or application)

Q14 (Reusable insights: The paper provides reusable insights (i.e. the capacity to gain an accurate and deep understanding). Such insights may go beyond the scope of the paper, domain or application, in order to build up consistent knowledge across the MIR community.)

Agree

Q15 (Please explain your assessment of reusable insights in the paper.)

The paper's cutpoint-based rearrangement technique offers reusable insights for real-time audio adaptation in contexts like gaming or interactive media, where dynamic, structure-aware music manipulation enhances user engagement. Additionally, its dual-mode system design and user-centric evaluation framework provide a template for context-aware systems balancing algorithmic precision with real-world spontaneity.

Q16 (Write ONE line (in your own words) with the main take-home message from the paper.)

The authors' RISE system pioneers real-time music restructuring using structure-aware analysis and cutpoint transitions to dynamically align song energy peaks with exercise intensity, enhancing workout.

Q17 (Would you recommend this paper for an award?)

No

Q19 (Potential to generate discourse: The paper will generate discourse at the ISMIR conference or have a large influence/impact on the future of the ISMIR community.)

Agree

Q20 (Overall evaluation: Keep in mind that minor flaws can be corrected, and should not be a reason to reject a paper. Please familiarize yourself with the reviewer guidelines at https://ismir.net/reviewer-guidelines)

Strong accept

Q21 (Main review and comments for the authors. Please summarize strengths and weaknesses of the paper. It is essential that you justify the reason for the overall evaluation score in detail. Keep in mind that belittling or sarcastic comments are not appropriate.)

This work presents a timely and compelling contribution to music information retrieval (MIR) by addressing a critical gap in adaptive music systems for exercise. The authors’ core innovation—real-time music rearrangement to align musical intensity with workout phases—represents a significant advancement over existing approaches that operate at the song or tempo level. By integrating computational structure analysis (Section 3.1) with cutpoint-based rearrangement (Section 3.2), the authors demonstrate how adaptive music can be dynamically tailored to users’ exertion states while preserving perceptual seamlessness. This dual focus on structural granularity and real-time adaptability is novel and addresses a longstanding challenge in context-aware music systems.

The methodological rigor is commendable. The preprocessing pipeline (beat detection, drum isolation, and intensity estimation) is well-justified, leveraging established MIR tools while introducing domain-specific adaptations (e.g., drum track LUFS thresholds). The two usage modes (guided/unguided) thoughtfully accommodate diverse exercise routines, expanding the system’s practical utility. The quantitative evaluation (Section 4) and mixed-methods user study (Section 5) provide robust evidence of both technical efficacy (transparency of transitions) and experiential benefits (enhanced motivation). Notably, participants’ reports of “pushing through” workouts due to aligned intensity peaks (Section 5.3) highlight the real-world impact of this work.

This paper sets a foundation for future research in adaptive music beyond exercise (e.g., gaming, productivity). While limitations like manual state input are acknowledged, the proposed solutions (sensor integration, generative audio inpainting) point to promising directions. Overall, the authors deliver a cohesive, user-centered contribution that bridges MIR techniques with behavioral science—a hallmark of impactful ISMIR research. I recommend acceptance.

Q2 ( I am an expert on the topic of the paper.)

Strongly disagree

Q3 (The title and abstract reflect the content of the paper.)

Strongly disagree

Q4 (The paper discusses, cites and compares with all relevant related work)

Agree

Q6 (Readability and paper organization: The writing and language are clear and structured in a logical manner.)

Agree

Q7 (The paper adheres to ISMIR 2025 submission guidelines (uses the ISMIR 2025 template, has at most 6 pages of technical content followed by “n” pages of references or ethical considerations, references are well formatted). If you selected “No”, please explain the issue in your comments.)

Yes

Q8 (Relevance of the topic to ISMIR: The topic of the paper is relevant to the ISMIR community. Note that submissions of novel music-related topics, tasks, and applications are highly encouraged. If you think that the paper has merit but does not exactly match the topics of ISMIR, please do not simply reject the paper but instead communicate this to the Program Committee Chairs. Please do not penalize the paper when the proposed method can also be applied to non-music domains if it is shown to be useful in music domains.)

Strongly agree

Q9 (Scholarly/scientific quality: The content is scientifically correct.)

Disagree

Q10 (Please justify the previous choice (Required if "Strongly Disagree" or "Disagree" is chosen, otherwise write "n/a"))

It is a very practical idea with a simple execution. Cutpoint detection (which relies on rather old algorithms) and the simple state machine can be considered as the main scientific contributions, but I doubt the scientific significance of these. Overall I think it is a decent startup idea converted to a paper, but how the user 'exercise intensity' is inferred is not mentioned at all... What specific device is used for this purpose? There is a section called 'participant and apparatus', but I cannot see the apparatus. How reliable or fast it is for identifying the high/low intensity? Only at the section 6: 'limitation and future work' we see that there is no sensing technology, and the user has to enter everything manually... If that is the case, this should be clarified throughout the paper.

Q11 (Novelty of the paper: The paper provides novel methods, applications, findings or results. Please do not narrowly view "novelty" as only new methods or theories. Papers proposing novel musical applications of existing methods from other research fields are considered novel at ISMIR conferences.)

Agree

Q12 (The paper provides all the necessary details or material to reproduce the results described in the paper. Keep in mind that ISMIR respects the diversity of academic disciplines, backgrounds, and approaches. Although ISMIR has a tradition of publishing open datasets and open-source projects to enhance the scientific reproducibility, ISMIR accepts submissions using proprietary datasets and implementations that are not sharable. Please do not simply reject the paper when proprietary datasets or implementations are used.)

Strongly disagree

Q13 (Pioneering proposals: This paper proposes a novel topic, task or application. Since this is intended to encourage brave new ideas and challenges, papers rated "Strongly Agree" and "Agree" can be highlighted, but please do not penalize papers rated "Disagree" or "Strongly Disagree". Keep in mind that it is often difficult to provide baseline comparisons for novel topics, tasks, or applications. If you think that the novelty is high but the evaluation is weak, please do not simply reject the paper but carefully assess the value of the paper for the community.)

Disagree (Standard topic, task, or application)

Q14 (Reusable insights: The paper provides reusable insights (i.e. the capacity to gain an accurate and deep understanding). Such insights may go beyond the scope of the paper, domain or application, in order to build up consistent knowledge across the MIR community.)

Disagree

Q15 (Please explain your assessment of reusable insights in the paper.)

In an average person's life, one main purpose of music is providing motivation while doing other activities. This paper addresses the problem of synchronizing music to workout sets, and the idea has big applicability in everyday life.

Q16 (Write ONE line (in your own words) with the main take-home message from the paper.)

A music looping machine can be used to boost motivation in guided interval training.

Q17 (Would you recommend this paper for an award?)

No

Q19 (Potential to generate discourse: The paper will generate discourse at the ISMIR conference or have a large influence/impact on the future of the ISMIR community.)

Disagree

Q20 (Overall evaluation: Keep in mind that minor flaws can be corrected, and should not be a reason to reject a paper. Please familiarize yourself with the reviewer guidelines at https://ismir.net/reviewer-guidelines)

Weak accept

Q21 (Main review and comments for the authors. Please summarize strengths and weaknesses of the paper. It is essential that you justify the reason for the overall evaluation score in detail. Keep in mind that belittling or sarcastic comments are not appropriate.)

This paper introduces a music-looping state machine aimed at enhancing workout sessions. The concept is promising, especially if the authors plan to commercialize it. However, the title and abstract is misleading: What is presented is a decent method for mixing piece sections for guided interval training: neither rearrangement, nor Realtime Intensity Synchronization with Exercise... Outside this overselling issue, from a scientific perspective, the paper lacks novelty and does not offer a meaningful methodological contribution. It is best categorized as an application-focused paper. The limitations in its applicability need to be stated more clearly. If accepted, the authors should explicitly mention the absence of an automated intensity detection mechanism in the abstract. Major Concerns: Manual Input of Intensity Levels: A major limitation is the need for manual input of 'high' and 'low' intensity segments. This significantly reduces the system’s practicality. While the paper implies that detecting intensity changes is straightforward, the lack of an automated detection mechanism is a serious omission. This should be acknowledged earlier in the paper, not buried in the limitations section. Real-time, reliable detection of workout intensity is a non-trivial challenge, and the current framing is misleading. Lack of Scientific Contribution: The methods used for estimating segment intensities and determining cutpoints rely on existing techniques without any meaningful adaptation or innovation. There is no novel insight or technical advancement presented. Guided vs. Unguided Use: The guided mode shows some promise, but the unguided mode fails to deliver reliable results. This limits the system’s usefulness in real-world, unsupervised scenarios. I appreciate the creativity behind the work. It’s borderline for acceptance. If accepted, the paper should be clearly framed as a proof-of-concept application without misleading the conference participants. The lack of automated intensity detection should be stated upfront, and the structure should be revised to avoid the overselling issue. Clarifying these limitations would improve the paper’s impact and help set appropriate expectations

Q2 ( I am an expert on the topic of the paper.)

Disagree

Q3 (The title and abstract reflect the content of the paper.)

Agree

Q4 (The paper discusses, cites and compares with all relevant related work)

Disagree

Q5 (Please justify the previous choice (Required if “Strongly Disagree” or “Disagree” is chosen, otherwise write "n/a"))

The key techniques used in the task are not well-discussed.

Q6 (Readability and paper organization: The writing and language are clear and structured in a logical manner.)

Disagree

Q7 (The paper adheres to ISMIR 2025 submission guidelines (uses the ISMIR 2025 template, has at most 6 pages of technical content followed by “n” pages of references or ethical considerations, references are well formatted). If you selected “No”, please explain the issue in your comments.)

Yes

Q8 (Relevance of the topic to ISMIR: The topic of the paper is relevant to the ISMIR community. Note that submissions of novel music-related topics, tasks, and applications are highly encouraged. If you think that the paper has merit but does not exactly match the topics of ISMIR, please do not simply reject the paper but instead communicate this to the Program Committee Chairs. Please do not penalize the paper when the proposed method can also be applied to non-music domains if it is shown to be useful in music domains.)

Agree

Q9 (Scholarly/scientific quality: The content is scientifically correct.)

Agree

Q11 (Novelty of the paper: The paper provides novel methods, applications, findings or results. Please do not narrowly view "novelty" as only new methods or theories. Papers proposing novel musical applications of existing methods from other research fields are considered novel at ISMIR conferences.)

Strongly agree

Q12 (The paper provides all the necessary details or material to reproduce the results described in the paper. Keep in mind that ISMIR respects the diversity of academic disciplines, backgrounds, and approaches. Although ISMIR has a tradition of publishing open datasets and open-source projects to enhance the scientific reproducibility, ISMIR accepts submissions using proprietary datasets and implementations that are not sharable. Please do not simply reject the paper when proprietary datasets or implementations are used.)

Disagree

Q13 (Pioneering proposals: This paper proposes a novel topic, task or application. Since this is intended to encourage brave new ideas and challenges, papers rated "Strongly Agree" and "Agree" can be highlighted, but please do not penalize papers rated "Disagree" or "Strongly Disagree". Keep in mind that it is often difficult to provide baseline comparisons for novel topics, tasks, or applications. If you think that the novelty is high but the evaluation is weak, please do not simply reject the paper but carefully assess the value of the paper for the community.)

Strongly Agree (Very novel topic, task, or application)

Q14 (Reusable insights: The paper provides reusable insights (i.e. the capacity to gain an accurate and deep understanding). Such insights may go beyond the scope of the paper, domain or application, in order to build up consistent knowledge across the MIR community.)

Disagree

Q15 (Please explain your assessment of reusable insights in the paper.)

The paper lacks a thoughtful discussion on the task itself.

Q16 (Write ONE line (in your own words) with the main take-home message from the paper.)

A new MIR application for enhancing the workout experience through music rearrangement.

Q17 (Would you recommend this paper for an award?)

No

Q19 (Potential to generate discourse: The paper will generate discourse at the ISMIR conference or have a large influence/impact on the future of the ISMIR community.)

Agree

Q20 (Overall evaluation: Keep in mind that minor flaws can be corrected, and should not be a reason to reject a paper. Please familiarize yourself with the reviewer guidelines at https://ismir.net/reviewer-guidelines)

Weak accept

Q21 (Main review and comments for the authors. Please summarize strengths and weaknesses of the paper. It is essential that you justify the reason for the overall evaluation score in detail. Keep in mind that belittling or sarcastic comments are not appropriate.)

This paper proposes a system that rearranges a given music based on the user’s state during a workout. The system leverages several existing MIR techniques (e.g., music structure analysis, source separation, and beat tracking) to process a given music and synchronizes the processed music with the workout state based on the exertion state. In addition, a demonstration video regarding the use case of the proposed system is provided, which is very fascinating and helpful.

This is an interesting topic and application for the MIR research. The authors demonstrate how the existing MIR techniques can improve human activities from a different angle. One major concern is that the manuscript lacks a discussion on the task itself. How did the authors formulate the task? (Note that “intensity” as a key idea for the synchronization is not explicitly defined. Also, the use of loudness as a proxy of intensity is not clarified and justified.) Which parts of the task are most challenging? How did the authors deal with those parts? How did the authors make the design choices? Such kinds of discussion would provide more insights into the task and facilitate related research. The authors may consider reducing the size of the figures to make space for including more discussions.

Similarly, a thorough discussion on the key techniques used in the system (e.g., the all-in-one model and Spleeter) would be required. The authors may provide a brief introduction to each of the techniques in Section 2 for readers who might not be familiar with these methods. In addition, it would be helpful if the authors could provide an overview of the system before addressing the details.

Overall, this is quite an interesting work, and I think there is enough time for the authors to revise the manuscript to address the aforementioned issues. Therefore, I evaluated it as a "Weak Accept."

Other comments: - Lines 2-4 and lines 10-12 might seem redundant. - Line 162: The definition of “a cutpoint” is somewhat weird. “A cutpoint tuple/pair/set” might be some alternatives. - Line 175: incorrect indent before “where”