{"type":"ScholarlyArticle","title":"Learning Neural Vocoder from Range-Null Space Decomposition","authors":[{"name":"Andong Li","slug":"andong-li","given":"Andong","family":"Li","affiliation":""},{"name":"Tong Lei","slug":"tong-lei","given":"Tong","family":"Lei","affiliation":""},{"name":"Zhihang Sun","slug":"zhihang-sun","given":"Zhihang","family":"Sun","affiliation":""},{"name":"Rilin Chen","slug":"rilin-chen","given":"Rilin","family":"Chen","affiliation":""},{"name":"Erwei Yin","slug":"erwei-yin","given":"Erwei","family":"Yin","affiliation":""},{"name":"Xiaodong Li","slug":"xiaodong-li","given":"Xiaodong","family":"Li","affiliation":""},{"name":"Chengshi Zheng","slug":"chengshi-zheng","given":"Chengshi","family":"Zheng","affiliation":""}],"abstract":"Despite the rapid development of neural vocoders in recent years, they usually suffer from some intrinsic challenges like opaque modeling, and parameter-performance trade-off. In this study, we propose an innovative time-frequency (T-F) domain-based neural vocoder to resolve the above-mentioned challenges. To be specific, we bridge the connection between the classical signal range-null decomposition (RND) theory and vocoder task, and the reconstruction of target spectrogram can be decomposed into the superimposition between the range-space and null-space, where the former is enabled by a linear domain shift from the original mel-scale domain to the target linear-scale domain, and the latter is instantiated via a learnable network for further spectral detail generation. Accordingly, we propose a novel dual-path framework, where the spectrum is hierarchically encoded/decoded, and the cross- and narrow-band modules are elaborately devised for efficient sub-band  and sequential modeling. Comprehensive experiments are conducted on the LJSpeech and LibriTTS benchmarks. Quantitative and qualitative results show that while enjoying lightweight network parameters, the proposed approach yields state-of-the-art performance among existing advanced methods. Our code and the pretrained model weights are available at https://github.com/Andong-Li-speech/RNDVoC.","doi":"10.24963/ijcai.2025/904","url":"https://ijcai.org/proceedings/2025/904","pdf":"https://ijcai.org/proceedings/2025/0904.pdf","markdown":"https://ijcai.org/proceedings/2025/904.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/904","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Natural Language Processing","track":"Main Track","number":904,"pages":{"first":8131,"last":8140},"keywords":["Machine Learning: ML: Applications","Natural Language Processing: NLP: Tools","Natural Language Processing: NLP: Speech"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}