Multimodal models show great potential in tasks such as generating language, video, and musical scores. However, they still face problems such as emotional consistency and professional guidance for background music generation tasks oriented toward rich melodic elements. In this paper, we propose multidimensional interaction guidance and temporal scaling encoding to generate music vector representations with multidimensional interaction properties by embedding emotion labels, rhythmic density, and rhythmic intensity into music expression compound words. We design the background music transformer (BMT), a model for generating film and television soundtracks with rhythmic and harmonic correspondence between video and music, and provide a corresponding unpaired data-driven network training method for the model. We propose a “creator-audience” dual-view evaluation strategy to evaluate the interactivity and soundtrack effect of the model in a more comprehensive way. The experimental results show that the BMT model improves the objective evaluation index by 20.6%, and the model inference efficiency increases from 0.125 to 14.370, and also has obvious advantages in subjective evaluation index.
音乐、画面和情绪之间存在着一致性效应已被心理学研究证实[7]。影视作品的内容与背景音乐和谐统一,是感染观众的重要条件[8],采用与电影画面相同情感表达的音乐,能快速唤起观众情绪,引发观众共鸣[9-10]。但现有的视频配乐生成模型忽略了视频内容与生成音乐情感之间的协调一致性。例如可控音乐转换器模型 (controllable music transformer, CMT)[11]主要关注视频与音乐之间的节奏匹配,未能有效利用对应关系来增强情感表达或激发观众情感共鸣。理想的背景音乐应与影视内容具备相同的情感倾向[12-13],这一点在现有研究中尚未得到足够重视,也是本文试图解决的关键问题之一。
实现人工专业引导与深度神经网络自动创作之间的平衡,对于个性化和创新性音乐生成至关重要[14-15],恰当的人机交互指导能确保模型既能理解创作者的意图,又能充分发挥其创造潜力[16]。然而现有的背景音乐生成方法在人工引导控制上较为单一,未能充分考虑音乐情感、节奏、速度、乐器等多维度交互控制。例如CMT[11]和双线性转换器模型(double linear transformer, DLT)[17]虽然提供了与视频节奏的交互参数,但未包括对音乐的情感、演奏速度、节奏提取方式以及演奏乐器等关键因素的控制,限制了音乐生成的多样性和适应性。
2)提出面向丰富曲调要素的影视配乐生成模型(background music transformer, BMT)。设计非成对数据驱动方法,采用视觉节奏节拍模型 (visual rhythm and beat, Visbeat)[21]建立视频与音乐的节奏对应关系。使用节奏、显著性阈值进行局部控制,以情感类别和使用的乐器进行全局控制。
Kaliakatsos-PapakostasM, FlorosA, VrahatisM N. Artificial intelligence methods for music generation: a review and future perspectives[M]//Nature-Inspired Computation and Swarm Intelligence. Amsterdam: Elsevier, 2020: 217-245. DOI: 10.1016/b978-0-12-819714-1.00024-5 .
[7]
TesorieroM, RickardN S. Music-enhanced recall: an effect of mood congruence, emotion arousal or emotion function? [J]. Musicae Scientiae, 2012, 16(3): 340-356. DOI: 10.1177/1029864912459046 .
[8]
MilletB, ChattahJ, AhnS. Soundtrack design: the impact of music on visual attention and affective responses[J]. Applied Ergonomics, 2021, 93: 103301. DOI: 10.1016/j.apergo.2020.103301 .
[9]
VästfjällD. Emotion induction through music: a review of the musical mood induction procedure[J]. Musicae Scientiae, 2001, 5(): 173-211. DOI: 10.1177/10298649020050S107 .
[10]
BachorikJ P, BangertM, LouiP, et al. Emotion in motion: investigating the time-course of emotional judgments of musical stimuli[J]. Music Perception, 2009, 26(4): 355-364. DOI: 10.1525/mp.2009.26.4.355 .
[11]
DiS Z, JiangZ R, LiuS, et al. Video background music generation with controllable music transformer[C]//Proceedings of the 29th ACM International Conference on Multimedia. October 20 - 24, 2021, Virtual Event, China. ACM, 2021: 2037-2045. DOI: 10.1145/3474085.3475195 .
[12]
FerreiraL N, MouL L, WhiteheadJ, et al. Controlling perceived emotion in symbolic music generation with Monte Carlo Tree search[C]//Proceedings of the Eighteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. 2022, 18(1): 163-170. ACM, 2022: 163-170. DOI: 10.1609/aiide.v18i1.21960 .
[13]
Gómez-CañónJ S, CanoE, EerolaT, et al. Music emotion recognition: toward new, robust standards in personalized and context-sensitive applications[J]. IEEE Signal Processing Magazine, 2021, 38(6): 106-114. DOI: 10.1109/MSP.2021.3106232 .
[14]
WuX P. An analysis of the origin, integration and development of contemporary music composition and artificial intelligence and human-computer interaction[C]//International Conference on Human-Computer Interaction. Cham: Springer Nature Switzerland, 2023: 259-268. DOI: 10.1007/978-3-031-34609-5_19 .
[15]
BriotJ P. From artificial neural networks to deep learning for music generation: history, concepts and trends[J]. Neural Computing and Applications, 2021, 33(1): 39-65. DOI: 10.1007/s00521-020-05399-0 .
[16]
WangL, ZhaoZ Y, LiuH W, et al. A review of intelligent music generation systems[J]. Neural Computing and Applications, 2024, 36(12): 6381-6401. DOI: 10.1007/s00521-024-09418-2 .
[17]
YangX T, YuY, WuX Y. Double linear transformer for background music generation from videos[J]. Applied Sciences, 2022, 12(10): 5050. DOI: 10.3390/app12105050 .
[18]
KarlinF, WrightR. On the track: a guide to contemporary film scoring[M]. New York: Schirmer Books, 1990. DOI: 10.4324/9780203643907 .
[19]
WuS L, YangY H. The Jazz Transformer on the front line: exploring the shortcomings of AI-composed music through quantitative measures[EB/OL]. arXiv 2020:2008.01307. (2020-08-04)[2024-02-26].
[20]
HsiaoW Y, LiuJ Y, YehY C, et al. Compound word transformer: learning to compose full-song music over dynamic directed hypergraphs[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(1): 178-186. DOI: 10.1609/aaai.v35i1.16091 .
[21]
DavisA, AgrawalaM. Visual rhythm and beat[J]. ACM Transactions on Graphics, 2018, 37(4): 122. DOI: 10.1145/3197517.3201371 .
[22]
Hernandez-OlivanC, BeltrnJ R. Music composition with deep learning: a review [M]//. Advances in Speech and Music Technology . Cham: Springer, 2023: 25-50. DOI: 10.1007/978-3-031-18444-4_2 .
[23]
HuangY S, YangY H. Pop music transformer: beat-based modeling and generation of expressive pop piano compositions[C]//Proceedings of the 28th ACM International Conference on Multimedia. Seattle WA USA. ACM, 2020: 1180-1188. DOI: 10.1145/3394171.3413671 .
[24]
EerolaT, ToiviainenP. MIDI toolbox: MATLAB tools for music research [EB/OL]. University of Jyväskylä, Finland.(2017-05-17)[2024-02-26].
[25]
HungH T, ChingJ, DohS, et al. EMOPIA: a multi-modal pop piano dataset for emotion recognition and emotion-based music generation [EB/OL]. arXiv 2021:2108.01374. (2021-08-03)[2024-02-26].
[26]
SulunS, DaviesM E P, VianaP. Symbolic music generation conditioned on continuous-valued emotions[J]. IEEE Access, 2022, 10: 44617-44626. DOI: 10.1109/ACCESS.2022.3169744 .
[27]
PesekM, StrleG, KavčičA, et al. The Moodo dataset: integrating user context with emotional and color perception of music for affective music information retrieval[J]. Journal of New Music Research, 2017, 46(3): 246-260. DOI: 10.1080/09298215.2017.1333518 .
[28]
RussellJ A. A circumplex model of affect[J]. Journal of Personality and Social Psychology, 1980, 39(6): 1161-1178. DOI: 10.1037/H0077714 .
[29]
KatharopoulosA, VyasA, PappasN, et al. Transformers are RNNs: fast autoregressive transformers with linear attention[EB/OL]. arXiv 2020: 2006.16236. (2020-06-29) [2024-02-26].
[30]
RaeJ W, PotapenkoA, JayakumarS M, et al. Compressive transformers for long-range sequence modelling[EB/OL]. arXiv 2019:1911.05507. (2019-11-13)[2024-02-26].
[31]
DaiZ H, YangZ L, YangY M, et al. Transformer-XL: attentive language models beyond a fixed-length context[C]//proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy. Stroudsburg, PA, USA: Association for Computational Linguistics, 2019: 2978-2988. DOI: 10.18653/v1/p19-1285 .
[32]
VaswaniA, ShazeerN, ParmarN, et al. Attention is all you need [EB/OL]. arXiv 2017:1706.03762.(2017-06-12) [2024-02-26].