- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper clarifies that existing approaches generate lyrics without inferring sections to organize the complete lyrics, so the authors propose SMILE, which can generate lyrics considering both music passages and external content. SMILE first infers the structure from the whole music, then analyzes the structure and generates lyrics temporally aligned with the music syllables, with paragraph refinement before output. Experimental results show that some metrics are improved using SMILE than other baselines.
Critical strengths
- define a new pipeline that generates lyrics considering both music and external supplied content;
- propose an algorithm to distinguish sections only from the music itself, and propose a planning process before lyrics generation with a global refinement after generation. The pipeline sounds complete and useful;
- some metrics are improved using this pipeline.
Critical weaknesses
- It seems that this work only proposes a pipeline with some tricks in algorithm, but without improvement in model structure;
- I am not sure whether the proposed algorithm can make sense, for example, in MSA, can the probability be correctly inferred only with hidden state input? Is it more reasonable to use attention network which can take the contextual relationship into consideration?
- The experimental results highly depend on oracle and reference contents, it cannot confirm the general generation ability of the model;
- The evaluation set is tiny for objective experiment and there is no human evaluation to support the conclusion.
- The ablation study seems that "time + line" cannot outperform "time only" and "line only" in most metrics,.
- I am not sure whether numbers like "[0.898, 6.319]" in Line 395 and "[−14.58, 39.58]" in Line 431 refer to the 95%CI (because no explanation), if yes, the average of these two numbers seems not equal to the number in front of it, and the interval is too wide which undermines the credibility
Questions for authors
- Is there any improvement in the model structure? or just define a new pipeline with some tricks in algorithm?
- Can SMILE generate lyrics without reference paragraph, line intervals, syllable counts, etc.? And how is the performance?
- "These sources may be combined within one method." are stated in Introduction, so how can SMILE generates lyrics from both external prompts and the original music? Is there any cross-attention module or other adaptors?
- Is there any universality evaluation of using more samples not from the same distribution or any subjective evaluation results?