Papers with Code 아카이브
Speaker Diarization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 15
- 보존된 평가 기록
- 40
Speaker Diarization is the task of segmenting and co-indexing audio recordings by speaker. The way the task is commonly defined, the goal is not to identify known speakers, but to co-index segments that are attributed to the same speaker; in other words, diarization implies finding speaker boundaries and grouping segments that belong to the same speaker, and, as a by-product, determining the number of distinct speakers. In combination with speech recognition, diarization enables speaker-attributed speech-to-text transcription.
Source: Improving Diarization Robustness using Diversification, Randomization and the DOVER Algorithm
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/hitachi-speech/EEND
공식 코드End-to-End Neural Speaker Diarization with Permutation-Free Objectives
https://github.com/hltcoe/VBx
공식 코드Speaker Diarization using Two-pass Leave-One-Out Gaussian PLDA Clustering of DNN Embeddings
https://github.com/idiap/bert-text-diarization-atc
공식 코드https://github.com/iiscleap/DIHARD_2019_baseline_alltracks
공식 코드The Second DIHARD Diarization Challenge: Dataset, task, and baselines
https://github.com/iiscleap/SSC
공식 코드Self-supervised Representation Learning With Path Integral Clustering For Speaker Diarization
https://github.com/iiscleap/selfsup_plda
공식 코드Self-Supervised Metric Learning With Graph Clustering For Speaker Diarization
https://github.com/jaesunghuh/voxsrc2022
공식 코드VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge
https://github.com/jialuli3/speechbrain
공식 코드https://github.com/joonaskalda/pixit
공식 코드https://github.com/juanmc2005/streamingspeakerdiarization
공식 코드Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation
https://github.com/junhua-liao/light-asd
공식 코드https://github.com/jwhitehill/compositionalclustering
공식 코드Compositional Clustering: Applications to Multi-Label Object Recognition and Speaker Identification
https://github.com/liyunlongaaa/nsd-ms2s
공식 코드https://github.com/marianne-m/brouhaha-vad
공식 코드https://github.com/modelscope/3D-Speaker
공식 코드3D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and Diarization
https://github.com/mu-y/diarist
공식 코드DiariST: Streaming Speech Translation with Speaker Diarization
https://github.com/nikhilraghav29/sc-pna
공식 코드https://github.com/nttcslab-sp/eend-vector-clustering
공식 코드https://github.com/ol-mega/ppca
공식 코드Long-term Conversation Analysis: Exploring Utility and Privacy
https://github.com/prachiisc/SHARC
공식 코드End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarization
https://github.com/pyannote/pyannote-audio
공식 코드pyannote.audio: neural building blocks for speaker diarization
https://github.com/rhoposit/icassp2021
공식 코드Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm
https://github.com/rub-ksv/spatial-stream-weights
공식 코드https://github.com/showlab/ava-avd
공식 코드https://github.com/speechbrain/speechbrain
공식 코드https://github.com/speechclub/cder_metric
공식 코드https://github.com/tango4j/Auto-Tuning-Spectral-Clustering
공식 코드Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengap
https://github.com/taoruijie/mfv-ksd
공식 코드Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization
https://github.com/usc-sail/child-adult-diarization
공식 코드Exploring Speech Foundation Models for Speaker Diarization in Child-Adult Dyadic Interactions
https://github.com/vishalshar/SpeakerDiarization_RNN_CNN_LSTM
공식 코드https://github.com/wq2012/SpectralCluster
공식 코드https://github.com/x-lance/ber
공식 코드https://github.com/zaharah/ood_audio
공식 코드On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors
https://github.com/zcxu-eric/ava-avd
공식 코드https://github.com/zqs01/multi-channel-wav2vec2
공식 코드Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.