ResearchTrend.AI
Simulating realistic speech overlaps improves multi-talker ASR

Simulating realistic speech overlaps improves multi-talker ASR

Muqiao Yang
Naoyuki Kanda
Xiaofei Wang
Jian Wu
S. Sivasankaran
Zhuo Chen
Jinyu Li
Takuya Yoshioka
ArXivPDFHTML

Papers citing "Simulating realistic speech overlaps improves multi-talker ASR"

4 / 4 papers shown
Title
MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models
MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models
Thai-Binh Nguyen
Alexander Waibel
74
1
0
27 Nov 2024
Target conversation extraction: Source separation using turn-taking dynamics
Target conversation extraction: Source separation using turn-taking dynamics
Tuochao Chen
Qirui Wang
Bohan Wu
Malek Itani
Sefik Emre Eskimez
Takuya Yoshioka
Shyamnath Gollakota
20
4
0
15 Jul 2024
End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation
End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation
Juan Pablo Zuluaga
Zhaocheng Huang
Xing Niu
Rohit Paturi
S. Srinivasan
Prashant Mathur
Brian Thompson
Marcello Federico
BDL
27
2
0
01 Nov 2023
BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASR
BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASR
Yuhao Liang
Fan Yu
Yangze Li
Pengcheng Guo
Shiliang Zhang
Qian Chen
Linfu Xie
27
7
0
23 May 2023