mlsanityData to 14 Oct 2026

NAS-FM: Neural Architecture Search for Tunable and Interpretable Sound Synthesis based on Frequency Modulation

arXiv 2305.12868 ↗First posted 22 May 2023cs.SD cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Developing digital sound synthesizers is crucial to the music industry as it provides a low-cost way to produce high-quality sounds with rich timbres. Existing traditional synthesizers often require substantial expertise to determine the overall framework of a synthesizer and the parameters of submodules. Since expert knowledge is hard to acquire, it hinders the flexibility to quickly design and tune digital synthesizers for diverse sounds. In this paper, we propose ``NAS-FM'', which adopts neural architecture search (NAS) to build a differentiable frequency modulation (FM) synthesizer. Tunable synthesizers with interpretable controls can be developed automatically from sounds without any prior expert knowledge and manual operating costs. In detail, we train a supernet with a specifically designed search space, including predicting the envelopes of carriers and modulators with different frequency ratios. An evolutionary search algorithm with adaptive oscillator size is then developed to find the optimal relationship between oscillators and the frequency ratio of FM. Extensive experiments on recordings of different instrument sounds show that our algorithm can build a synthesizer fully automatically, achieving better results than handcrafted synthesizers. Audio samples are available at https://nas-fm.github.io/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 37 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

21 of 37 references.

References · 21

  1. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  2. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  3. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  4. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  5. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  6. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  7. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
  8. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
  9. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 309
  10. 2018Fr'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithmscited by 225
  11. 2018Efficient Neural Audio Synthesiscited by 219
  12. 2020DDSP: Differentiable Digital Signal Processingcited by 178
9 more
  1. 2019GANSynth: Adversarial Neural Audio Synthesiscited by 116
  2. 2016SampleRNN: An Unconditional End-to-End Neural Audio Generation Modelcited by 110
  3. 2018CREPE: A Convolutional Representation for Pitch Estimationcited by 110
  4. 2016Creating A Multi-track Classical Musical Performance Dataset for Multimodal Music Analysis: Challenges, Insights, and Applicationscited by 61
  5. 2021NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Searchcited by 56
  6. 2021Analyzing and Mitigating Interference in Neural Architecture Searchcited by 20
  7. 2021OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detectioncited by 19
  8. 2022DDX7: Differentiable FM Synthesis of Musical Instrument Soundscited by 13
  9. 2022Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimationcited by 7

Built on by

Not cited yet.