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

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Speaker Diarization

논문

Efficient and Generalizable Speaker Diarization via Structured Pruning of Self-Supervised Models

M3SD: Multi-modal, Multi-scenario and Multi-language Speaker Diarization Dataset

Exploring Speaker Diarization with Mixture of Experts

Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models

SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition

Diarization-Aware Multi-Speaker Automatic Speech Recognition via Large Language Models

Improving Neural Diarization through Speaker Attribute Attractors and Local Dependency Modeling

Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm

Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization

Pretraining Multi-Speaker Identification for Neural Speaker Diarization

Multi-Channel Sequence-to-Sequence Neural Diarization: Experimental Results for The MISP 2025 Challenge

HPP-Voice: A Large-Scale Evaluation of Speech Embeddings for Multi-Phenotypic Classification

VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering

The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition

Multi-Stage Speaker Diarization for Noisy Classrooms

Speaker Diarization for Low-Resource Languages Through Wav2vec Fine-Tuning

SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniors

Microphone Array Geometry Independent Multi-Talker Distant ASR: NTT System for the DASR Task of the CHiME-8 Challenge

Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond

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

Language Modelling for Speaker Diarization in Telephonic Interviews

SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models

Universal Speaker Embedding Free Target Speaker Extraction and Personal Voice Activity Detection

Unsupervised Speech Segmentation: A General Approach Using Speech Language Models

DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition

TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch

Comprehensive Audio Query Handling System with Integrated Expert Models and Contextual Understanding

Automating Feedback Analysis in Surgical Training: Detection, Categorization, and Assessment

Disentangled-Transformer: An Explainable End-to-End Automatic Speech Recognition Model with Speech Content-Context Separation

Sequence-to-Sequence Neural Diarization with Automatic Speaker Detection and Representation

DCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition under Realistic Single-Channel Conditions

Guided Speaker Embedding

Incorporating Spatial Cues in Modular Speaker Diarization for Multi-channel Multi-party Meetings

On the calibration of powerset speaker diarization models

META-CAT: Speaker-Informed Speech Embeddings via Meta Information Concatenation for Multi-talker ASR

TCG CREST System Description for the Second DISPLACE Challenge