ICASSP (IEEE International Conference on Acoustics, Speech and Signal Processing)
是IEEE最大的訊號處理研討會,包含聲音、影像等
也是每年新技術的前瞻發表會
AASP-L1: detection and classification of acoustic scenes and events i AASP-L2: detection and classification of acoustic scenes and events ii AASP-L3: source separation and speech enhancement i AASP-L4: source separation and speech enhancement ii AASP-L5: spatial audio recording and reproduction AASP-L6: music signal analysis, processing and synthesis AASP-L7: music information retrieval AASP-P1: acoustic environments and music analysis AASP-P2: music source separation and spatial audio AASP-P3: auditory modeling, music information retrieval and bioacoustics AASP-P4: source separation and music information retrieval AASP-P5: sensor array processing and auditory modeling AASP-P6: music signal analysis and multimedia AASP-P7: active noise control, source separation, and system identification AASP-P8: spatial audio, audio enhancement and bandwidth extension AASP-P9: quality measures and sensor array processing AASP-P10: audio security and source separation AASP-P11: audio coding and acoustic event detection AASP-P12: sensor array processing and medical acoustics AASP-P13: acoustic scene classification and music signal analysis AASP-P14: acoustic event detection and speech enhancement AASP-P15: spatial audio recording and detection and classification of acoustic scenes and events AASP-P16: music signal analysis, feedback and echo cancellation and equalization
SAM-P3: beamforming and source separation SAM-P4: localization and tracking SAM-P5: detection, estimation and classification
SLP-L1: end-to-end speech recognition i: general topics SLP-L2: end-to-end speech recognition ii: new models SLP-L3: novel architectures and training strategies for asr SLP-L4: feature learning and adapation for asr SLP-L5: speech enhancement i SLP-L6: systems for speaker recognition and identification SLP-L7: diarization and speaker characterization SLP-L8: analysis of voice, speech and language disorders i SLP-L9: using multiple perspectives in emotion and sentiment analysis SLP-L10: speech synthesis i SLP-L11: models of speech production SLP-P1: multi-lingual identification and processing SLP-P2: speaker verification and identification i SLP-P3: multi-lingual speech recognition SLP-P4: speaker verification and identification ii SLP-P5: end-to-end speech recognition iii: source integration and knowledge transfer SLP-P6: features and robustness for speaker identification SLP-P7: end-to-end speech recognition iv: training strategies SLP-P8: features and learning for speaker identification and diarization SLP-P9: keyword spotting and embedded asr systems SLP-P10: analysis of voice, speech and language disorders ii SLP-P11: asr training strategies and toolkits SLP-P12: speech analysis SLP-P13: new features, models and representations / audio visual asr SLP-P14: speech analysis of extralinguistic factors SLP-P15: distant speech recognition SLP-P16: architectures for emotion and sentiment analysis SLP-P17: robust speech recognition SLP-P18: voice conversion SLP-P19: speech enhancement ii SLP-P20: speech synthesis ii SLP-P21: speech separation, enhancement and denoising SLP-P22: speech synthesis iii SLP-P23: end-to-end speech recognition v: modeling methods SLP-P24: speech coding and perception
HLT-L1: applications: translation, summarization, qa HLT-P1: language modeling, asr and punctuation prediction
SS-P1: recent advances in the active control of sound