Proxy-supervised joint fine-tuning of a BSRNN separator with ASR, speaker-similarity, VAD and DNSMOS losses on a new 71k real-conversation corpus yields the best SIM and timing F1 on REAL-T.
High fidelity speech enhancement with band-split rnn
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Despite the rapid progress in speech enhancement (SE) research, enhancing the quality of desired speech in environments with strong noise and interfering speakers remains challenging. In this paper, we extend the application of the recently proposed band-split RNN (BSRNN) model to full-band SE and personalized SE (PSE) tasks. To mitigate the effects of unstable high-frequency components in full-band speech, we perform bi-directional and uni-directional band-level modeling to low-frequency and high-frequency subbands, respectively. For PSE task, we incorporate a speaker enrollment module into BSRNN to utilize target speaker information. Moreover, we utilize a MetricGAN discriminator (MGD) and a multi-resolution spectrogram discriminator (MRSD) to improve perceptual quality metrics. Experimental results show that our system outperforms various top-ranking SE systems, achieves state-of-the-art (SOTA) results on the DNS-2020 test set and ranks among the top 3 in the DNS-2023 challenge.
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
Kimi-Audio is an open-source audio foundation model that achieves state-of-the-art results on speech recognition, audio understanding, question answering, and conversation after pre-training on more than 13 million hours of speech, sound, and music data.
citing papers explorer
-
PS4: Proxy-Supervised Joint Training for Real Target Speaker Extraction
Proxy-supervised joint fine-tuning of a BSRNN separator with ASR, speaker-similarity, VAD and DNSMOS losses on a new 71k real-conversation corpus yields the best SIM and timing F1 on REAL-T.
-
Kimi-Audio Technical Report
Kimi-Audio is an open-source audio foundation model that achieves state-of-the-art results on speech recognition, audio understanding, question answering, and conversation after pre-training on more than 13 million hours of speech, sound, and music data.