今日论文合集：cs.SD语音16篇，eess.AS音频处理18篇。cs.SD语音【1】 Synthia's Melody: A Benchmark Framework for Unsupervised Domain Adaptation in Audio链接：https://arxiv.org/abs/2309.15024作者：Chia-Hsin Lin, Charles Jones, Björn W. Schuller, Harry Coppock【2】 Updated Corpora and Benchmarks for Long-Form Speech Recognition链接：https://arxiv.org/abs/2309.15013作者：Jennifer Drexler Fox, Desh Raj, Natalie Delworth, Quinn McNamara, Corey Miller, Migüel Jetté备注：Submitted to ICASSP 2024【3】 Emphasized Non-Target Speaker Knowledge in Knowledge Distillation for Automatic Speaker Verification链接：https://arxiv.org/abs/2309.14838作者：Duc-Tuan Truong, Ruijie Tao, Jia Qi Yip, Kong Aik Lee, Eng Siong Chng备注：Submitted to ICASSP 2024【4】 Speech Audio Synthesis from Tagged MRI and Non-Negative Matrix Factorization via Plastic Transformer链接：https://arxiv.org/abs/2309.14586作者：Xiaofeng Liu, Fangxu Xing, Maureen Stone, Jiachen Zhuo, Sidney Fels, Jerry L. Prince, Georges El Fakhri, Jonghye Woo备注：MICCAI 2023 (Oral presentation)【5】 Joint Audio and Speech Understanding链接：https://arxiv.org/abs/2309.14405作者：Yuan Gong, Alexander H. Liu, Hongyin Luo, Leonid Karlinsky, James Glass备注：Accepted at ASRU 2023. Interactive demo at this https URL【6】 Towards using Cough for Respiratory Disease Diagnosis by leveraging Artificial Intelligence: A Survey链接：https://arxiv.org/abs/2309.14383作者：Aneeqa Ijaz, Muhammad Nabeel, Usama Masood, Tahir Mahmood, Mydah Sajid Hashmi, Iryna Posokhova, Ali Rizwan, Ali Imran备注：30 pages, 12 figures, 9 tables【7】 Human Transcription Quality Improvement链接：https://arxiv.org/abs/2309.14372作者：Jian Gao, Hanbo Sun, Cheng Cao, Zheng Du备注：5 pages, 3 figures, 5 tables, INTERSPEECH 2023【8】 Simultaneously Learning Speaker's Direction and Head Orientation from Binaural Recordings链接：https://arxiv.org/abs/2309.15064作者：Harshvardhan Takawale, Nirupam Roy【9】 Segment-Level Vectorized Beam Search Based on Partially Autoregressive Inference链接：https://arxiv.org/abs/2309.14922作者：Masao Someki, Nicholas Eng, Yosuke Higuchi, Shinji Watanabe备注：Accepted at ASRU 2023【10】 Optimization Techniques for a Physical Model of Human Vocalisation链接：https://arxiv.org/abs/2309.14761作者：Mateo Cámara, Zhiyuan Xu, Yisu Zong, José Luis Blanco, Joshua D. Reiss备注：Accepted to DAFx 2023【11】 Exploring RWKV for Memory Efficient and Low Latency Streaming ASR链接：https://arxiv.org/abs/2309.14758作者：Keyu An, Shiliang Zhang备注：submitted to ICASSP 2024【12】 Rethinking Session Variability: Leveraging Session Embeddings for Session Robustness in Speaker Verification链接：https://arxiv.org/abs/2309.14741作者：Hee-Soo Heo, KiHyun Nam, Bong-Jin Lee, Youngki Kwon, Minjae Lee, You Jin Kim, Joon Son Chung【13】 NoLACE: Improving Low-Complexity Speech Codec Enhancement Through Adaptive Temporal Shaping链接：https://arxiv.org/abs/2309.14521作者：Jan Büthe, Ahmed Mustafa, Jean-Marc Valin, Karim Helwani, Michael M. Goodwin备注：submitted to ICASSP 2024【14】 Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity链接：https://arxiv.org/abs/2309.14507作者：Krishna Subramani, Jean-Marc Valin, Jan Buethe, Paris Smaragdis, Mike Goodwin备注：Submitted to ICASSP 2024, 5 pages【15】 On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks "In-the-Wild''链接：https://arxiv.org/abs/2309.14462作者：Arthur Pimentel, Heitor Guimarães, Anderson R. Avila, Mehdi Rezagholizadeh, Tiago H. Falk【16】 Online Active Learning For Sound Event Detection链接：https://arxiv.org/abs/2309.14460作者：Mark Lindsey, Ankit Shah, Francis Kubala, Richard M. Stern备注：Submitted to ICASSP 2024. Publication will belong to IEEEeess.AS音频处理【1】 Simultaneously Learning Speaker's Direction and Head Orientation from Binaural Recordings链接：https://arxiv.org/abs/2309.15064作者：Harshvardhan Takawale, Nirupam Roy【2】 Segment-Level Vectorized Beam Search Based on Partially Autoregressive Inference链接：https://arxiv.org/abs/2309.14922作者：Masao Someki, Nicholas Eng, Yosuke Higuchi, Shinji Watanabe备注：Accepted at ASRU 2023【3】 Optimization Techniques for a Physical Model of Human Vocalisation链接：https://arxiv.org/abs/2309.14761作者：Mateo Cámara, Zhiyuan Xu, Yisu Zong, José Luis Blanco, Joshua D. Reiss备注：Accepted to DAFx 2023【4】 Exploring RWKV for Memory Efficient and Low Latency Streaming ASR链接：https://arxiv.org/abs/2309.14758作者：Keyu An, Shiliang Zhang备注：submitted to ICASSP 2024【5】 Rethinking Session Variability: Leveraging Session Embeddings for Session Robustness in Speaker Verification链接：https://arxiv.org/abs/2309.14741作者：Hee-Soo Heo, KiHyun Nam, Bong-Jin Lee, Youngki Kwon, Minjae Lee, You Jin Kim, Joon Son Chung【6】 NoLACE: Improving Low-Complexity Speech Codec Enhancement Through Adaptive Temporal Shaping链接：https://arxiv.org/abs/2309.14521作者：Jan Büthe, Ahmed Mustafa, Jean-Marc Valin, Karim Helwani, Michael M. Goodwin备注：submitted to ICASSP 2024【7】 Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity链接：https://arxiv.org/abs/2309.14507作者：Krishna Subramani, Jean-Marc Valin, Jan Buethe, Paris Smaragdis, Mike Goodwin备注：Submitted to ICASSP 2024, 5 pages【8】 On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks "In-the-Wild''链接：https://arxiv.org/abs/2309.14462作者：Arthur Pimentel, Heitor Guimarães, Anderson R. Avila, Mehdi Rezagholizadeh, Tiago H. Falk【9】 Online Active Learning For Sound Event Detection链接：https://arxiv.org/abs/2309.14460作者：Mark Lindsey, Ankit Shah, Francis Kubala, Richard M. Stern备注：Submitted to ICASSP 2024. Publication will belong to IEEE【10】 Privacy-preserving and Privacy-attacking Approaches for Speech and Audio -- A Survey链接：https://arxiv.org/abs/2309.15087作者：Yuchen Liu, Apu Kapadia, Donald Williamson【11】 Synthia's Melody: A Benchmark Framework for Unsupervised Domain Adaptation in Audio链接：https://arxiv.org/abs/2309.15024作者：Chia-Hsin Lin, Charles Jones, Björn W. Schuller, Harry Coppock【12】 Updated Corpora and Benchmarks for Long-Form Speech Recognition链接：https://arxiv.org/abs/2309.15013作者：Jennifer Drexler Fox, Desh Raj, Natalie Delworth, Quinn McNamara, Corey Miller, Migüel Jetté备注：Submitted to ICASSP 2024【13】 Emphasized Non-Target Speaker Knowledge in Knowledge Distillation for Automatic Speaker Verification链接：https://arxiv.org/abs/2309.14838作者：Duc-Tuan Truong, Ruijie Tao, Jia Qi Yip, Kong Aik Lee, Eng Siong Chng备注：Submitted to ICASSP 2024【14】 Speech Audio Synthesis from Tagged MRI and Non-Negative Matrix Factorization via Plastic Transformer链接：https://arxiv.org/abs/2309.14586作者：Xiaofeng Liu, Fangxu Xing, Maureen Stone, Jiachen Zhuo, Sidney Fels, Jerry L. Prince, Georges El Fakhri, Jonghye Woo备注：MICCAI 2023 (Oral presentation)【15】 Joint Audio and Speech Understanding链接：https://arxiv.org/abs/2309.14405作者：Yuan Gong, Alexander H. Liu, Hongyin Luo, Leonid Karlinsky, James Glass备注：Accepted at ASRU 2023. Interactive demo at this https URL【16】 Seeing and hearing what has not been said; A multimodal client behavior classifier in Motivational Interviewing with interpretable fusion链接：https://arxiv.org/abs/2309.14398作者：Lucie Galland, Catherine Pelachaud, Florian Pecune备注：9 pages, 7 figures【17】 Towards using Cough for Respiratory Disease Diagnosis by leveraging Artificial Intelligence: A Survey链接：https://arxiv.org/abs/2309.14383作者：Aneeqa Ijaz, Muhammad Nabeel, Usama Masood, Tahir Mahmood, Mydah Sajid Hashmi, Iryna Posokhova, Ali Rizwan, Ali Imran备注：30 pages, 12 figures, 9 tables【18】 Human Transcription Quality Improvement链接：https://arxiv.org/abs/2309.14372作者：Jian Gao, Hanbo Sun, Cheng Cao, Zheng Du备注：5 pages, 3 figures, 5 tables, INTERSPEECH 2023机器翻译，仅供参考
每日语音速递
