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.
Wanna hear your voice? A sample is all we need!
Incorporating Spatial Cues in Modular Speaker Diarization for Multi-channel Multi-party Meetings
Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration
Target Speaker ASR with Whisper
DualSep: A Light-weight dual-encoder convolutional recurrent network for real-time in-car speech separation
USEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction
LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization
Improving Generalization of Speech Separation in Real-World Scenarios: Strategies in Simulation, Optimization, and Evaluation
Enhanced Reverberation as Supervision for Unsupervised Speech Separation
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing
Robustness of Speech Separation Models for Similar-pitch Speakers
TalTech-IRIT-LIS Speaker and Language Diarization Systems for DISPLACE 2024
Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis
Knowledge boosting during low-latency inference
Papez: Resource-Efficient Speech Separation with Auditory Working Memory
Audio-Visual Approach For Multimodal Concurrent Speaker Detection
Towards Audio Codec-based Speech Separation
Text-aware Speech Separation for Multi-talker Keyword Spotting
AV-CrossNet: an Audiovisual Complex Spectral Mapping Network for Speech Separation By Leveraging Narrow- and Cross-Band Modeling
Enhanced Deep Speech Separation in Clustered Ad Hoc Distributed Microphone Environments
Transcription-Free Fine-Tuning of Speech Separation Models for Noisy and Reverberant Multi-Speaker Automatic Speech Recognition
Multimodal Representation Loss Between Timed Text and Audio for Regularized Speech Separation
Noise-robust Speech Separation with Fast Generative Correction
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation
Cross-Talk Reduction
Effects of Dataset Sampling Rate for Noise Cancellation through Deep Learning
Look Once to Hear: Target Speech Hearing with Noisy Examples
Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction
SPMamba: State-space model is all you need in speech separation
Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation
Robust Active Speaker Detection in Noisy Environments
PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings
Target Speech Extraction with Pre-trained Self-supervised Learning Models
Probing Self-supervised Learning Models with Target Speech Extraction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.