今日论文合集：cs.SD语音47篇，eess.AS音频处理47篇。
cs.SD语音
【1】 Instruction-Following Speech Recognition标题：跟随指令的语音识别作者：Cheng-I Jeff Lai,Zhiyun Lu,Liangliang Cao,Ruoming Pang链接：http://arxiv.org/pdf/2309.09843v1
【2】 Hypr: A comprehensive study for ASR hypothesis revising with a reference corpus标题：Hypr：参考语料库对ASR假设修正的综合研究作者：Yi-Wei Wang,Ke-Han Lu,Kuan-Yu Chen备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09838v1
【3】 Frame-to-Utterance Convergence: A Spectra-Temporal Approach for Unified Spoofing Detection标题：帧-话语收敛：一种统一欺骗检测的谱-时间方法作者：Awais Khan,Khalid Mahmood Malik,Shah Nawaz链接：http://arxiv.org/pdf/2309.09837v1【4】 Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement标题：观察说话人：一种用于情感解缠对话中情感识别的混合连续归因网络作者：Shanglin Lei,Xiaoping Wang,Guanting Dong,Jiang Li,Yingjian Liu链接：http://arxiv.org/pdf/2309.09799v1【5】 Synth-AC: Enhancing Audio Captioning with Synthetic Supervision标题：Synth-AC：通过综合监控增强音频字幕作者：Feiyang Xiao,Qiaoxi Zhu,Jian Guan,Xubo Liu,Haohe Liu,Kejia Zhang,Wenwu Wang链接：http://arxiv.org/pdf/2309.09705v1【6】 Do learned speech symbols follow Zipf's law?标题：习得的言语符号是否遵循齐普夫定律？作者：Shinnosuke Takamichi,Hiroki Maeda,Joonyong Park,Daisuke Saito,Hiroshi Saruwatari备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09690v1【7】 Speeding Up Speech Synthesis In Diffusion Models By Reducing Data Distribution Recovery Steps Via Content Transfer标题：通过内容传输减少数据分发恢复步骤来加速扩散模型中的语音合成作者：Peter Ochieng备注：10 pages链接：http://arxiv.org/pdf/2309.09652v1【8】 Electrolaryngeal Speech Intelligibility Enhancement Through Robust Linguistic Encoders标题：通过健壮的语言编码器增强喉电语音的清晰度作者：Lester Phillip Violeta,Wen-Chin Huang,Ding Ma,Ryuichi Yamamoto,Kazuhiro Kobayashi,Tomoki Toda备注：Submitted to ICASSP 2024. Demo page: lesterphillip.github.ioicassp2024_el_sie链接：http://arxiv.org/pdf/2309.09627v1【9】 HumTrans: A Novel Open-Source Dataset for Humming Melody Transcription and Beyond标题：HumTrans：一种用于哼唱旋律转录和超越的新型开源数据集作者：Shansong Liu,Xu Li,Dian Li,Ying Shan链接：http://arxiv.org/pdf/2309.09623v1【10】 Spoofing attack augmentation: can differently-trained attack models improve generalisation?标题：欺骗攻击增强：不同训练的攻击模型能否提高泛化能力？作者：Wanying Ge,Xin Wang,Junichi Yamagishi,Massimiliano Todisco,Nicholas Evans备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09586v1【11】 Face-Driven Zero-Shot Voice Conversion with Memory-based Face-Voice Alignment标题：基于记忆的人脸-语音对齐的人脸驱动Zero-Shot语音转换作者：Zheng-Yan Sheng,Yang Ai,Yan-Nian Chen,Zhen-Hua Ling链接：http://arxiv.org/pdf/2309.09470v1【12】 Spiking-LEAF: A Learnable Auditory front-end for Spiking Neural Networks标题：穗叶：一种用于尖峰神经网络的可学习听觉前端作者：Zeyang Song,Jibin Wu,Malu Zhang,Mike Zheng Shou,Haizhou Li链接：http://arxiv.org/pdf/2309.09469v1
【13】 Are Soft Prompts Good Zero-shot Learners for Speech Recognition?标题：软提示是语音识别的好零拍子吗？作者：Dianwen Ng,Chong Zhang,Ruixi Zhang,Yukun Ma,Fabian Ritter-Gutierrez,Trung Hieu Nguyen,Chongjia Ni,Shengkui Zhao,Eng Siong Chng,Bin Ma链接：http://arxiv.org/pdf/2309.09413v1【14】 Augmenting text for spoken language understanding with Large Language Models标题：利用大型语言模型扩充用于口语理解的文本作者：Roshan Sharma,Suyoun Kim,Daniel Lazar,Trang Le,Akshat Shrivastava,Kwanghoon Ahn,Piyush Kansal,Leda Sari,Ozlem Kalinli,Michael Seltzer备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09390v1
【15】 A Few-Shot Approach to Dysarthric Speech Intelligibility Level Classification Using Transformers标题：一种基于Transformer的语音清晰度分级方法作者：Paleti Nikhil Chowdary,Vadlapudi Sai Aravind,Gorantla V N S L Vishnu Vardhan,Menta Sai Akshay,Menta Sai Aashish,Jyothish Lal. G备注：Paper has been presented at ICCCNT 2023 and the final version will be published in IEEE Digital Library Xplore链接：http://arxiv.org/pdf/2309.09329v1【16】 Sound Source Distance Estimation in Diverse and Dynamic Acoustic Conditions标题：多种动态声学条件下的声源距离估计作者：Saksham Singh Kushwaha,Iran R. Roman,Magdalena Fuentes,Juan Pablo Bello备注：Accepted in WASPAA 2023链接：http://arxiv.org/pdf/2309.09288v1
【17】 Zero- and Few-shot Sound Event Localization and Detection标题：零点和少点声事件的定位与检测作者：Kazuki Shimada,Kengo Uchida,Yuichiro Koyama,Takashi Shibuya,Shusuke Takahashi,Yuki Mitsufuji,Tatsuya Kawahara备注：5 pages, 4 figures链接：http://arxiv.org/pdf/2309.09223v1【18】 Enhancing Quantised End-to-End ASR Models via Personalisation标题：通过个性化增强量化的端到端ASR模型作者：Qiuming Zhao,Guangzhi Sun,Chao Zhang,Mingxing Xu,Thomas Fang Zheng备注：5 pages, submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09136v1【19】 Enhancing GAN-Based Vocoders with Contrastive Learning Under Data-limited Condition标题：数据受限条件下基于对比学习的GaN声码器增强作者：Haoming Guo,Seth Z. Zhao,Jiachen Lian,Gopala Anumanchipalli,Gerald Friedland链接：http://arxiv.org/pdf/2309.09088v1【20】 SynthTab: Leveraging Synthesized Data for Guitar Tablature Transcription标题：SynthTab：利用合成数据进行吉他表转录作者：Yongyi Zang,Yi Zhong,Frank Cwitkowitz,Zhiyao Duan备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.09085v1【21】 Music Generation based on Generative Adversarial Networks with Transformer标题：基于带Transformer的产生式对抗性网络的音乐生成作者：Ziyi Jiang,Yi Zhong,Ruoxue Wu,Zhenghan Chen,Xiaoxuan Liang备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.09075v1【22】 Regularized Contrastive Pre-training for Few-shot Bioacoustic Sound Detection标题：基于正则化对比预训练的小炮声生物声学检测作者：Ilyass Moummad,Romain Serizel,Nicolas Farrugia链接：http://arxiv.org/pdf/2309.08971v1【23】 Contrastive Latent Space Reconstruction Learning for Audio-Text Retrieval标题：用于音频文本检索的对比潜在空间重构学习作者：Kaiyi Luo,Xulong Zhang,Jianzong Wang,Huaxiong Li,Ning Cheng,Jing Xiao备注：Accepted by The 35th IEEE International Conference on Tools with Artificial Intelligence. (ICTAI 2023)链接：http://arxiv.org/pdf/2309.08839v1【24】 FastGraphTTS: An Ultrafast Syntax-Aware Speech Synthesis Framework标题：FastGraphTTS：一种超快语法感知语音合成框架作者：Jianzong Wang,Xulong Zhang,Aolan Sun,Ning Cheng,Jing Xiao备注：Accepted by The 35th IEEE International Conference on Tools with Artificial Intelligence. (ICTAI 2023)链接：http://arxiv.org/pdf/2309.08837v1【25】 Enhance audio generation controllability through representation similarity regularization标题：通过表示相似正则化增强音频生成的可控性作者：Yangyang Shi,Gael Le Lan,Varun Nagaraja,Zhaoheng Ni,Xinhao Mei,Ernie Chang,Forrest Iandola,Yang Liu,Vikas Chandra备注：5 pages链接：http://arxiv.org/pdf/2309.08773v1【26】 Diverse Neural Audio Embeddings -- Bringing Features back !标题：多样化的神经音频嵌入--带回功能！作者：Prateek Verma备注：6 pages, 1 figure, 2 table链接：http://arxiv.org/pdf/2309.08751v1【27】 Investigating End-to-End ASR Architectures for Long Form Audio Transcription标题：长格式音频转录的端到端ASR体系结构研究作者：Nithin Rao Koluguri,Samuel Kriman,Georgy Zelenfroind,Somshubra Majumdar,Dima Rekesh,Vahid Noroozi,Jagadeesh Balam,Boris Ginsburg备注：PrePrint. Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09950v1【28】 Distilling HuBERT with LSTMs via Decoupled Knowledge Distillation标题：基于解耦知识蒸馏的LSTMS提取休BERT作者：Danilo de Oliveira,Timo Gerkmann备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09920v1【29】 RECAP: Retrieval-Augmented Audio Captioning标题：概述：检索-增强音频字幕作者：Sreyan Ghosh,Sonal Kumar,Chandra Kiran Reddy Evuru,Ramani Duraiswami,Dinesh Manocha备注：Code and data soon here: this https URL链接：http://arxiv.org/pdf/2309.09836v1【30】 Single and Few-step Diffusion for Generative Speech Enhancement标题：用于生成性语音增强的单步和分步扩散算法作者：Bunlong Lay,Jean-Marie Lemercier,Julius Richter,Timo Gerkmann备注：5 pages, 1 figure, 1 table链接：http://arxiv.org/pdf/2309.09677v1【31】 Scaling the time and Fourier domains to align periodically and their convolution标题：对时间域和傅立叶域进行缩放以定期对齐及其卷积作者：Matthew R. Flax,W. Harvey Holmes链接：http://arxiv.org/pdf/2309.09645v1【32】 Refining DNN-based Mask Estimation using CGMM-based EM Algorithm for Multi-channel Noise Reduction标题：基于CGMM的EM多通道降噪算法改进DNN掩码估计作者：Julitta Bartolewska,Stanisław Kacprzak,Konrad KowalczykJournal-ref：Proc. Interspeech 2022, 2923-2927 (2022)链接：http://arxiv.org/pdf/2309.09630v1【33】 Utilizing Whisper to Enhance Multi-Branched Speech Intelligibility Prediction Model for Hearing Aids标题：利用Whisper增强助听器多分支语音清晰度预测模型作者：Ryandhimas E. Zezario,Fei Chen,Chiou-Shann Fuh,Hsin-Min Wang,Yu Tsao链接：http://arxiv.org/pdf/2309.09548v1【34】 Training dynamic models using early exits for automatic speech recognition on resource-constrained devices标题：在资源受限的设备上使用提前退出训练动态模型以进行自动语音识别作者：George August Wright,Umberto Cappellazzo,Salah Zaiem,Desh Raj,Lucas Ondel Yang,Daniele Falavigna,Alessio Brutti链接：http://arxiv.org/pdf/2309.09546v1【35】 Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech标题：动态-卓越：迈向动态、协作、全面的语音教学调整基准作者：Chien-yu Huang,Ke-Han Lu,Shih-Heng Wang,Chi-Yuan Hsiao,Chun-Yi Kuan,Haibin Wu,Siddhant Arora,Kai-Wei Chang,Jiatong Shi,Yifan Peng,Roshan Sharma,Shinji Watanabe,Bhiksha Ramakrishnan,Shady Shehata,Hung-yi Lee备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09510v1【36】 HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform标题：HiFTNet：一种快速高质量的短时傅里叶逆滤波神经声码器作者：Yinghao Aaron Li,Cong Han,Xilin Jiang,Nima Mesgarani链接：http://arxiv.org/pdf/2309.09493v1【37】 Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter标题：通过语言提示调整和框架级语言适配器增强多语言语音识别作者：Song Li,Yonbin You,Xuezhi Wang,Ke Ding,Guanglu Wan备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.09443v1【38】 Continuous Modeling of the Denoising Process for Speech Enhancement Based on Deep Learning标题：基于深度学习的语音增强去噪过程连续建模作者：Zilu Guo,Jun Du,CHin-Hui Lee链接：http://arxiv.org/pdf/2309.09270v1【39】 PromptVC: Flexible Stylistic Voice Conversion in Latent Space Driven by Natural Language Prompts标题：PromptVC：自然语言提示驱动的潜在空间中灵活的文体语音转换作者：Jixun Yao,Yuguang Yang,Yi Lei,Ziqian Ning,Yanni Hu,Yu Pan,Jingjing Yin,Hongbin Zhou,Heng Lu,Lei Xie备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09262v1【40】 Improving Speech Inversion Through Self-Supervised Embeddings and Enhanced Tract Variables标题：基于自监督嵌入和增强轨迹变量的语音倒置改进作者：Ahmed Adel Attia,Yashish M. Siriwardena,Carol Espy-Wilson链接：http://arxiv.org/pdf/2309.09220v1【41】 Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding with Sequence-to-Sequence Architecture标题：基于序列到序列结构的记忆感知多说话人嵌入的神经说话人二值化作者：Gaobin Yang,Maokui He,Shutong Niu,Ruoyu Wang,Yanyan Yue,Shuangqing Qian,Shilong Wu,Jun Du,Chin-Hui Lee备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09180v1【42】 Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions标题：稳健性和保真度的统一：恶劣条件下语音增强的预先训练生成方法的综合研究作者：Heming Wang,Meng Yu,Hao Zhang,Chunlei Zhang,Zhongweiyang Xu,Muqiao Yang,Yixuan Zhang,Dong Yu备注：Paper in submission链接：http://arxiv.org/pdf/2309.09028v1【43】 Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation标题：具有CTC提示和文本数据增强的纯解码器语音识别架构作者：Emiru Tsunoo,Hayato Futami,Yosuke Kashiwagi,Siddhant Arora,Shinji Watanabe备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.08876v1【44】 Boosting End-to-End Multilingual Phoneme Recognition through Exploiting Universal Speech Attributes Constraints标题：利用通用语音属性约束提高端到端多语种音素识别作者：Hao Yen,Sabato Marco Siniscalchi,Chin-Hui Lee链接：http://arxiv.org/pdf/2309.08828v1
【45】 Stack-and-Delay: a new codebook pattern for music generation标题：Stack-and Delay：一种新的音乐生成码本模式作者：Gael Le Lan,Varun Nagaraja,Ernie Chang,David Kant,Zhaoheng Ni,Yangyang Shi,Forrest Iandola,Vikas Chandra链接：http://arxiv.org/pdf/2309.08804v1【46】 MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response标题：MusiLingo：将音乐和文本与预先训练的语言模型连接起来，用于音乐字幕和查询响应作者：Zihao Deng,Yinghao Ma,Yudong Liu,Rongchen Guo,Ge Zhang,Wenhu Chen,Wenhao Huang,Emmanouil Benetos链接：http://arxiv.org/pdf/2309.08730v1【47】 Music Source Separation Based on a Lightweight Deep Learning Framework (DTTNET: DUAL-PATH TFC-TDF UNET)标题：基于轻量级深度学习框架的音乐源分离(DTTNET：Dual-Path TFC-TDF UNET)作者：Junyu Chen,Susmitha Vekkot,Pancham Shukla备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08684v1

eess.AS音频处理
【1】 Investigating End-to-End ASR Architectures for Long Form Audio Transcription标题：长格式音频转录的端到端ASR体系结构研究作者：Nithin Rao Koluguri,Samuel Kriman,Georgy Zelenfroind,Somshubra Majumdar,Dima Rekesh,Vahid Noroozi,Jagadeesh Balam,Boris Ginsburg备注：PrePrint. Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09950v1
【2】 Distilling HuBERT with LSTMs via Decoupled Knowledge Distillation标题：基于解耦知识蒸馏的LSTMS提取休BERT作者：Danilo de Oliveira,Timo Gerkmann备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09920v1
【3】 RECAP: Retrieval-Augmented Audio Captioning标题：概述：检索-增强音频字幕作者：Sreyan Ghosh,Sonal Kumar,Chandra Kiran Reddy Evuru,Ramani Duraiswami,Dinesh Manocha备注：Code and data soon here: this https URL链接：http://arxiv.org/pdf/2309.09836v1【4】 Single and Few-step Diffusion for Generative Speech Enhancement标题：用于生成性语音增强的单步和分步扩散算法作者：Bunlong Lay,Jean-Marie Lemercier,Julius Richter,Timo Gerkmann备注：5 pages, 1 figure, 1 table链接：http://arxiv.org/pdf/2309.09677v1【5】 Scaling the time and Fourier domains to align periodically and their convolution标题：对时间域和傅立叶域进行缩放以定期对齐及其卷积作者：Matthew R. Flax,W. Harvey Holmes链接：http://arxiv.org/pdf/2309.09645v1【6】 Refining DNN-based Mask Estimation using CGMM-based EM Algorithm for Multi-channel Noise Reduction标题：基于CGMM的EM多通道降噪算法改进DNN掩码估计作者：Julitta Bartolewska,Stanisław Kacprzak,Konrad KowalczykJournal-ref：Proc. Interspeech 2022, 2923-2927 (2022)链接：http://arxiv.org/pdf/2309.09630v1【7】 Utilizing Whisper to Enhance Multi-Branched Speech Intelligibility Prediction Model for Hearing Aids标题：利用Whisper增强助听器多分支语音清晰度预测模型作者：Ryandhimas E. Zezario,Fei Chen,Chiou-Shann Fuh,Hsin-Min Wang,Yu Tsao链接：http://arxiv.org/pdf/2309.09548v1【8】 Training dynamic models using early exits for automatic speech recognition on resource-constrained devices标题：在资源受限的设备上使用提前退出训练动态模型以进行自动语音识别作者：George August Wright,Umberto Cappellazzo,Salah Zaiem,Desh Raj,Lucas Ondel Yang,Daniele Falavigna,Alessio Brutti链接：http://arxiv.org/pdf/2309.09546v1【9】 Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech标题：动态-卓越：迈向动态、协作、全面的语音教学调整基准作者：Chien-yu Huang,Ke-Han Lu,Shih-Heng Wang,Chi-Yuan Hsiao,Chun-Yi Kuan,Haibin Wu,Siddhant Arora,Kai-Wei Chang,Jiatong Shi,Yifan Peng,Roshan Sharma,Shinji Watanabe,Bhiksha Ramakrishnan,Shady Shehata,Hung-yi Lee备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09510v1【10】 HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform标题：HiFTNet：一种快速高质量的短时傅里叶逆滤波神经声码器作者：Yinghao Aaron Li,Cong Han,Xilin Jiang,Nima Mesgarani链接：http://arxiv.org/pdf/2309.09493v1【11】 Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter标题：通过语言提示调整和框架级语言适配器增强多语言语音识别作者：Song Li,Yonbin You,Xuezhi Wang,Ke Ding,Guanglu Wan备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.09443v1【12】 Continuous Modeling of the Denoising Process for Speech Enhancement Based on Deep Learning标题：基于深度学习的语音增强去噪过程连续建模作者：Zilu Guo,Jun Du,CHin-Hui Lee链接：http://arxiv.org/pdf/2309.09270v1【13】 PromptVC: Flexible Stylistic Voice Conversion in Latent Space Driven by Natural Language Prompts标题：PromptVC：自然语言提示驱动的潜在空间中灵活的文体语音转换作者：Jixun Yao,Yuguang Yang,Yi Lei,Ziqian Ning,Yanni Hu,Yu Pan,Jingjing Yin,Hongbin Zhou,Heng Lu,Lei Xie备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09262v1【14】 Improving Speech Inversion Through Self-Supervised Embeddings and Enhanced Tract Variables标题：基于自监督嵌入和增强轨迹变量的语音倒置改进作者：Ahmed Adel Attia,Yashish M. Siriwardena,Carol Espy-Wilson链接：http://arxiv.org/pdf/2309.09220v1【15】 Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding with Sequence-to-Sequence Architecture标题：基于序列到序列结构的记忆感知多说话人嵌入的神经说话人二值化作者：Gaobin Yang,Maokui He,Shutong Niu,Ruoyu Wang,Yanyan Yue,Shuangqing Qian,Shilong Wu,Jun Du,Chin-Hui Lee备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09180v1【16】 Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions标题：稳健性和保真度的统一：恶劣条件下语音增强的预先训练生成方法的综合研究作者：Heming Wang,Meng Yu,Hao Zhang,Chunlei Zhang,Zhongweiyang Xu,Muqiao Yang,Yixuan Zhang,Dong Yu备注：Paper in submission链接：http://arxiv.org/pdf/2309.09028v1【17】 Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation标题：具有CTC提示和文本数据增强的纯解码器语音识别架构作者：Emiru Tsunoo,Hayato Futami,Yosuke Kashiwagi,Siddhant Arora,Shinji Watanabe备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.08876v1【18】 Boosting End-to-End Multilingual Phoneme Recognition through Exploiting Universal Speech Attributes Constraints标题：利用通用语音属性约束提高端到端多语种音素识别作者：Hao Yen,Sabato Marco Siniscalchi,Chin-Hui Lee链接：http://arxiv.org/pdf/2309.08828v1【19】 Stack-and-Delay: a new codebook pattern for music generation标题：Stack-and Delay：一种新的音乐生成码本模式作者：Gael Le Lan,Varun Nagaraja,Ernie Chang,David Kant,Zhaoheng Ni,Yangyang Shi,Forrest Iandola,Vikas Chandra链接：http://arxiv.org/pdf/2309.08804v1【20】 MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response标题：MusiLingo：将音乐和文本与预先训练的语言模型连接起来，用于音乐字幕和查询响应作者：Zihao Deng,Yinghao Ma,Yudong Liu,Rongchen Guo,Ge Zhang,Wenhu Chen,Wenhao Huang,Emmanouil Benetos链接：http://arxiv.org/pdf/2309.08730v1【21】 Music Source Separation Based on a Lightweight Deep Learning Framework (DTTNET: DUAL-PATH TFC-TDF UNET)标题：基于轻量级深度学习框架的音乐源分离(DTTNET：Dual-Path TFC-TDF UNET)作者：Junyu Chen,Susmitha Vekkot,Pancham Shukla备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08684v1【22】 Instruction-Following Speech Recognition标题：跟随指令的语音识别作者：Cheng-I Jeff Lai,Zhiyun Lu,Liangliang Cao,Ruoming Pang链接：http://arxiv.org/pdf/2309.09843v1【23】 Hypr: A comprehensive study for ASR hypothesis revising with a reference corpus标题：Hypr：参考语料库对ASR假设修正的综合研究作者：Yi-Wei Wang,Ke-Han Lu,Kuan-Yu Chen备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09838v1【24】 Frame-to-Utterance Convergence: A Spectra-Temporal Approach for Unified Spoofing Detection标题：帧-话语收敛：一种统一欺骗检测的谱-时间方法作者：Awais Khan,Khalid Mahmood Malik,Shah Nawaz链接：http://arxiv.org/pdf/2309.09837v1【25】 Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement标题：观察说话人：一种用于情感解缠对话中情感识别的混合连续归因网络作者：Shanglin Lei,Xiaoping Wang,Guanting Dong,Jiang Li,Yingjian Liu链接：http://arxiv.org/pdf/2309.09799v1【26】 Synth-AC: Enhancing Audio Captioning with Synthetic Supervision标题：Synth-AC：通过综合监控增强音频字幕作者：Feiyang Xiao,Qiaoxi Zhu,Jian Guan,Xubo Liu,Haohe Liu,Kejia Zhang,Wenwu Wang链接：http://arxiv.org/pdf/2309.09705v1【27】 Do learned speech symbols follow Zipf's law?标题：习得的言语符号是否遵循齐普夫定律？作者：Shinnosuke Takamichi,Hiroki Maeda,Joonyong Park,Daisuke Saito,Hiroshi Saruwatari备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09690v1
【28】 Speeding Up Speech Synthesis In Diffusion Models By Reducing Data Distribution Recovery Steps Via Content Transfer标题：通过内容传输减少数据分发恢复步骤来加速扩散模型中的语音合成作者：Peter Ochieng备注：10 pages链接：http://arxiv.org/pdf/2309.09652v1【29】 Electrolaryngeal Speech Intelligibility Enhancement Through Robust Linguistic Encoders标题：通过健壮的语言编码器增强喉电语音的清晰度作者：Lester Phillip Violeta,Wen-Chin Huang,Ding Ma,Ryuichi Yamamoto,Kazuhiro Kobayashi,Tomoki Toda备注：Submitted to ICASSP 2024. Demo page: lesterphillip.github.ioicassp2024_el_sie链接：http://arxiv.org/pdf/2309.09627v1【30】 HumTrans: A Novel Open-Source Dataset for Humming Melody Transcription and Beyond标题：HumTrans：一种用于哼唱旋律转录和超越的新型开源数据集作者：Shansong Liu,Xu Li,Dian Li,Ying Shan链接：http://arxiv.org/pdf/2309.09623v1【31】 Spoofing attack augmentation: can differently-trained attack models improve generalisation?标题：欺骗攻击增强：不同训练的攻击模型能否提高泛化能力？作者：Wanying Ge,Xin Wang,Junichi Yamagishi,Massimiliano Todisco,Nicholas Evans备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09586v1【32】 Face-Driven Zero-Shot Voice Conversion with Memory-based Face-Voice Alignment标题：基于记忆的人脸-语音对齐的人脸驱动Zero-Shot语音转换作者：Zheng-Yan Sheng,Yang Ai,Yan-Nian Chen,Zhen-Hua Ling链接：http://arxiv.org/pdf/2309.09470v1【33】 Spiking-LEAF: A Learnable Auditory front-end for Spiking Neural Networks标题：穗叶：一种用于尖峰神经网络的可学习听觉前端作者：Zeyang Song,Jibin Wu,Malu Zhang,Mike Zheng Shou,Haizhou Li链接：http://arxiv.org/pdf/2309.09469v1【34】 Are Soft Prompts Good Zero-shot Learners for Speech Recognition?标题：软提示是语音识别的好零拍子吗？作者：Dianwen Ng,Chong Zhang,Ruixi Zhang,Yukun Ma,Fabian Ritter-Gutierrez,Trung Hieu Nguyen,Chongjia Ni,Shengkui Zhao,Eng Siong Chng,Bin Ma链接：http://arxiv.org/pdf/2309.09413v1【35】 Augmenting text for spoken language understanding with Large Language Models标题：利用大型语言模型扩充用于口语理解的文本作者：Roshan Sharma,Suyoun Kim,Daniel Lazar,Trang Le,Akshat Shrivastava,Kwanghoon Ahn,Piyush Kansal,Leda Sari,Ozlem Kalinli,Michael Seltzer备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09390v1【36】 A Few-Shot Approach to Dysarthric Speech Intelligibility Level Classification Using Transformers标题：一种基于Transformer的语音清晰度分级方法作者：Paleti Nikhil Chowdary,Vadlapudi Sai Aravind,Gorantla V N S L Vishnu Vardhan,Menta Sai Akshay,Menta Sai Aashish,Jyothish Lal. G备注：Paper has been presented at ICCCNT 2023 and the final version will be published in IEEE Digital Library Xplore链接：http://arxiv.org/pdf/2309.09329v1【37】 Sound Source Distance Estimation in Diverse and Dynamic Acoustic Conditions标题：多种动态声学条件下的声源距离估计作者：Saksham Singh Kushwaha,Iran R. Roman,Magdalena Fuentes,Juan Pablo Bello备注：Accepted in WASPAA 2023链接：http://arxiv.org/pdf/2309.09288v1【38】 Zero- and Few-shot Sound Event Localization and Detection标题：零点和少点声事件的定位与检测作者：Kazuki Shimada,Kengo Uchida,Yuichiro Koyama,Takashi Shibuya,Shusuke Takahashi,Yuki Mitsufuji,Tatsuya Kawahara备注：5 pages, 4 figures链接：http://arxiv.org/pdf/2309.09223v1【39】 Enhancing Quantised End-to-End ASR Models via Personalisation标题：通过个性化增强量化的端到端ASR模型作者：Qiuming Zhao,Guangzhi Sun,Chao Zhang,Mingxing Xu,Thomas Fang Zheng备注：5 pages, submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.09136v1【40】 Enhancing GAN-Based Vocoders with Contrastive Learning Under Data-limited Condition标题：数据受限条件下基于对比学习的GaN声码器增强作者：Haoming Guo,Seth Z. Zhao,Jiachen Lian,Gopala Anumanchipalli,Gerald Friedland链接：http://arxiv.org/pdf/2309.09088v1【41】 SynthTab: Leveraging Synthesized Data for Guitar Tablature Transcription标题：SynthTab：利用合成数据进行吉他表转录作者：Yongyi Zang,Yi Zhong,Frank Cwitkowitz,Zhiyao Duan备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.09085v1【42】 Music Generation based on Generative Adversarial Networks with Transformer标题：基于带Transformer的产生式对抗性网络的音乐生成作者：Ziyi Jiang,Yi Zhong,Ruoxue Wu,Zhenghan Chen,Xiaoxuan Liang备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.09075v1【43】 Regularized Contrastive Pre-training for Few-shot Bioacoustic Sound Detection标题：基于正则化对比预训练的小炮声生物声学检测作者：Ilyass Moummad,Romain Serizel,Nicolas Farrugia链接：http://arxiv.org/pdf/2309.08971v1【44】 Contrastive Latent Space Reconstruction Learning for Audio-Text Retrieval标题：用于音频文本检索的对比潜在空间重构学习作者：Kaiyi Luo,Xulong Zhang,Jianzong Wang,Huaxiong Li,Ning Cheng,Jing Xiao备注：Accepted by The 35th IEEE International Conference on Tools with Artificial Intelligence. (ICTAI 2023)链接：http://arxiv.org/pdf/2309.08839v1【45】 FastGraphTTS: An Ultrafast Syntax-Aware Speech Synthesis Framework标题：FastGraphTTS：一种超快语法感知语音合成框架作者：Jianzong Wang,Xulong Zhang,Aolan Sun,Ning Cheng,Jing Xiao备注：Accepted by The 35th IEEE International Conference on Tools with Artificial Intelligence. (ICTAI 2023)链接：http://arxiv.org/pdf/2309.08837v1【46】 Enhance audio generation controllability through representation similarity regularization标题：通过表示相似正则化增强音频生成的可控性作者：Yangyang Shi,Gael Le Lan,Varun Nagaraja,Zhaoheng Ni,Xinhao Mei,Ernie Chang,Forrest Iandola,Yang Liu,Vikas Chandra备注：5 pages链接：http://arxiv.org/pdf/2309.08773v1【47】 Diverse Neural Audio Embeddings -- Bringing Features back !标题：多样化的神经音频嵌入--带回功能！作者：Prateek Verma备注：6 pages, 1 figure, 2 table
链接：http://arxiv.org/pdf/2309.08751v1
机器翻译，仅供参考