{"type":"ScholarlyArticle","title":"BridgeVoC: Neural Vocoder with Schrödinger Bridge","authors":[{"name":"Tong Lei","slug":"tong-lei","given":"Tong","family":"Lei","affiliation":""},{"name":"Zhiyu Zhang","slug":"zhiyu-zhang","given":"Zhiyu","family":"Zhang","affiliation":""},{"name":"Rilin Chen","slug":"rilin-chen","given":"Rilin","family":"Chen","affiliation":""},{"name":"Meng Yu","slug":"meng-yu","given":"Meng","family":"Yu","affiliation":""},{"name":"Jing Lu","slug":"jing-lu","given":"Jing","family":"Lu","affiliation":""},{"name":"Chengshi Zheng","slug":"chengshi-zheng","given":"Chengshi","family":"Zheng","affiliation":""},{"name":"Dong Yu","slug":"dong-yu","given":"Dong","family":"Yu","affiliation":""},{"name":"Andong Li","slug":"andong-li","given":"Andong","family":"Li","affiliation":""}],"abstract":"While previous diffusion-based neural vocoders typically follow a noise-to-data generation pipe-line, the linear-degradation prior of the mel-spectrogram is often neglected, resulting in limited generation quality. By revisiting the vocoding task and excavating its connection with the signal restoration task, this paper proposes a time-frequency (T-F) domain-based neural vocoder with the Schrödinger Bridge, called BridgeVoC, which is the first to follow the data-to-data generation paradigm. Specifically, the mel-spectrogram can be projected into the target linear-scale domain and regarded as a degraded spectral representation with a deficient rank distribution. Based on this, the Schrödinger Bridge is leveraged to establish a connection between the degraded and target data distributions. During the inference stage, starting from the degraded representation, the target spectrum can be gradually restored rather than generated from a Gaussian noise process. Quantitative experiments on LJSpeech and LibriTTS show that BridgeVoC achieves faster inference and surpasses existing diffusion-based vocoder baselines, while also matching or exceeding non-diffusion state-of-the-art methods across evaluation metrics.","doi":"10.24963/ijcai.2025/903","url":"https://ijcai.org/proceedings/2025/903","pdf":"https://ijcai.org/proceedings/2025/0903.pdf","markdown":"https://ijcai.org/proceedings/2025/903.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/903","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":903,"pages":{"first":8122,"last":8130},"keywords":["Natural Language Processing: NLP: Speech","Natural Language Processing: NLP: Applications","Natural Language Processing: NLP: Information extraction"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}