Suchergebnisse - Electrical Engineering and Systems Science - Audio and Speech Processing

Large Language Models are Strong Audio-Visual Speech Recognition Learners

Autoren: Cappellazzo, Umberto Kim, Minsu Chen, Honglie et al.

Quelle: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Audio and Speech Processing (eess.AS), Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Multimedia, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing, Multimedia (cs.MM)

Zugangs-URL: http://arxiv.org/abs/2409.12319

Diffusion-based Unsupervised Audio-visual Speech Enhancement

Autoren: Ayilo, Jean-Eudes Sadeghi, Mostafa Serizel, Romain et al.

Weitere Verfasser: Ayilo, Jean-Eudes Sadeghi, Mostafa Serizel, Romain et al.

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: diffusion models, [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Signal Processing (eess.SP), FOS: Computer and information sciences, Computer Science - Machine Learning, Sound (cs.SD), [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Computer Science - Artificial Intelligence, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], unsupervised learning, audio-visual speech enhancement, Computer Science - Sound, Machine Learning (cs.LG), [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Artificial Intelligence (cs.AI), Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, posterior sampling, Electrical Engineering and Systems Science - Signal Processing, Electrical Engineering and Systems Science - Audio and Speech Processing

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2410.05301
https://hal.science/hal-04718254v2
https://hal.science/hal-04718254v2/document

Multi-Microphone Speech Emotion Recognition Using the Hierarchical Token-Semantic Audio Transformer Architecture

Autoren: Cohen, Ohad Hazan, Gershon Gannot, Sharon

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Electrical Engineering and Systems Science - Audio and Speech Processing, Machine Learning (cs.LG)

Zugangs-URL: http://arxiv.org/abs/2406.03272

Uncovering the Visual Contribution in Audio-Visual Speech Recognition

Autoren: Lin, Zhaofeng Harte, Naomi

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/abs/2412.17129

MACE: Leveraging Audio for Evaluating Audio Captioning Systems

Autoren: Dixit, Satvik Deshmukh, Soham Raj, Bhiksha

Quelle: 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW). :1-5

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/abs/2411.00321

Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio

Autoren: Barański, Mateusz Jasiński, Jan Bartolewska, Julitta et al.

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/abs/2501.11378

DCIM-AVSR: Efficient Audio-Visual Speech Recognition via Dual Conformer Interaction Module

Autoren: Wang, Xinyu Jiang, Haotian Huang, Haolin et al.

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/abs/2409.00481

Speech Enhancement Using Continuous Embeddings of Neural Audio Codec

Autoren: Li, Haoyang Yip, Jia Qi Fan, Tianyu et al.

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Computer Science - Machine Learning, Sound (cs.SD), Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing, Machine Learning (cs.LG)

Zugangs-URL: http://arxiv.org/abs/2502.16240

SCDiar: a streaming diarization system based on speaker change detection and speech recognition

Autoren: Zheng, Naijun Wan, Xucheng Liu, Kai et al.

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Audio and Speech Processing (eess.AS), Computer Science - Human-Computer Interaction, FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing, Human-Computer Interaction (cs.HC)

Zugangs-URL: http://arxiv.org/abs/2501.16641

Improving Lip-synchrony in Direct Audio-Visual Speech-to-Speech Translation

Autoren: Goncalves, Lucas Mathur, Prashant Niu, Xing et al.

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Computer Science - Computation and Language, Audio and Speech Processing (eess.AS), Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, FOS: Electrical engineering, electronic engineering, information engineering, Computation and Language (cs.CL), Computer Science - Sound, Computer Science - Multimedia, Electrical Engineering and Systems Science - Audio and Speech Processing, Multimedia (cs.MM)

Zugangs-URL: http://arxiv.org/abs/2412.16530

FLAMO: An Open-Source Library for Frequency-Domain Differentiable Audio Processing

Autoren: Santo, Gloria Dal De Bortoli, Gian Marco Prawda, Karolina et al.

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/abs/2409.08723

A Domain Adaptation Framework for Speech Recognition Systems with Only Synthetic data

Autoren: Tran, Minh Pang, Yutong Paul, Debjyoti et al.

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/abs/2501.12501

SAV-SE: Scene-Aware Audio-Visual Speech Enhancement With Selective State Space Model

Autoren: Xinyuan Qian Jiaran Gao Yaodan Zhang et al.

Quelle: IEEE Journal of Selected Topics in Signal Processing. 19:623-634

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Audio and Speech Processing (eess.AS), Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Sound, Computer Science - Multimedia, Electrical Engineering and Systems Science - Audio and Speech Processing, Multimedia (cs.MM)

Zugangs-URL: http://arxiv.org/abs/2411.07751

Audio Codec Augmentation for Robust Collaborative Watermarking of Speech Synthesis

Autoren: Juvela, Lauri Wang, Xin

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/abs/2409.13382

TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models

Autoren: Peng, Junyi Ashihara, Takanori Delcroix, Marc et al.

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Computer Science - Computation and Language, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computation and Language (cs.CL), Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/abs/2505.06660

BANC: Towards Efficient Binaural Audio Neural Codec for Overlapping Speech

Autoren: Ratnarajah, Anton Zhang, Shi-Xiong Yu, Dong

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/abs/2309.07416

Robust Audio-Visual Speech Enhancement: Correcting Misassignments in Complex Environments With Advanced Post-Processing

Autoren: Ren, Wenze Hung, Kuo-Hsuan Chao, Rong et al.

Quelle: 2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA). :1-6

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/abs/2409.14554

NEST: Self-supervised Fast Conformer as All-purpose Seasoning to Speech Processing Tasks

Autoren: Huang, He Park, Taejin Dhawan, Kunal et al.

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/abs/2408.13106

Improving Speech Enhancement by Cross- and Sub-band Processing with State Space Model

Autoren: Li, Jizhen Tu, Weiping Yang, Yuhong et al.

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/abs/2502.16207

Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics Processing

Autoren: Sarkar, Eklavya Doss, Mathew Magimai.

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Computer Science - Machine Learning, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Electrical Engineering and Systems Science - Audio and Speech Processing, Machine Learning (cs.LG)

Zugangs-URL: http://arxiv.org/abs/2501.05987