Papers with Code 아카이브
Speech Separation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 19
- 보존된 평가 기록
- 128
The task of extracting all overlapping speech sources in a given mixed speech signal refers to the Speech Separation. Speech Separation is a special scenario of source separation problem, where the focus is only on the overlapping speech signal sources and other interferences such as music or noise signals are not the main concern of the study. A recent representative Github project can be referred to ClearerVoice-Studio.
Source: A Unified Framework for Speech Separation
Image credit: Speech Separation of A Target Speaker Based on Deep Neural Networks
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Speaker activity driven neural speech extraction
Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks
VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency
Multi-channel Multi-frame ADL-MVDR for Target Speech Separation
Continuous Speech Separation Using Speaker Inventory for Long Multi-talker Recording
Group Communication with Context Codec for Lightweight Source Separation
Deep Ad-hoc Beamforming Based on Speaker Extraction for Target-Dependent Speech Separation
Audio-visual Speech Separation with Adversarially Disentangled Visual Representation
Multi-Decoder DPRNN: High Accuracy Source Counting and Separation
Ultra-Lightweight Speech Separation via Group Communication
WPD++: An Improved Neural Beamformer for Simultaneous Speech Separation and Dereverberation
Audio-visual Multi-channel Integration and Recognition of Overlapped Speech
Block-Online Guided Source Separation
Surrogate Source Model Learning for Determined Source Separation
On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments
ESPnet-se: end-to-end speech enhancement and separation toolkit designed for asr integration
Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis
Distributed speech separation in spatially unconstrained microphone arrays
Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training
Speakerfilter-Pro: an improved target speaker extractor combines the time domain and frequency domain
Attention is All You Need in Speech Separation
X-TaSNet: Robust and Accurate Time-Domain Speaker Extraction Network
Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer
Speech enhancement aided end-to-end multi-task learning for voice activity detection
Towards Listening to 10 People Simultaneously: An Efficient Permutation Invariant Training of Audio Source Separation Using Sinkhorn's Algorithm
BERT for Joint Multichannel Speech Dereverberation with Spatial-aware Tasks
Speaker Separation Using Speaker Inventories and Estimated Speech
Attention-based scaling adaptation for target speech extraction
The Cone of Silence: Speech Separation by Localization
Multi-microphone Complex Spectral Mapping for Utterance-wise and Continuous Speech Separation
X-DC: Explainable Deep Clustering based on Learnable Spectrogram Templates
An End-to-end Architecture of Online Multi-channel Speech Separation
Independent Vector Analysis via Log-Quadratically Penalized Quadratic Minimization
Independent Vector Analysis with Deep Neural Network Source Priors
An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.