Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Role Specific Lattice Rescoring for Speaker Role Recognition from Speech Recognition Outputs

Abstract: 

The language patterns followed by different speakers who play specific roles in conversational interactions provide valuable cues for the task of Speaker Role Recognition (SRR). Given the speech signal, existing algorithms typically try to find such patterns in the output of an Automatic Speech Recognition (ASR) system. In this work we propose an alternative way of revealing role-specific linguistic characteristics, by making use of role-specific ASR outputs, which are built by suitably rescoring the lattice produced after a first pass of ASR decoding. That way, we avoid pruning the lattice too early, eliminating the potential risk of information loss.

up
0 users have voted:

Paper Details

Authors:
David C. Atkins, Shrikanth Narayanan
Submitted On:
9 May 2019 - 3:15pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Nikolaos Flemotomos
Paper Code:
HLT-P2.10
Document Year:
2019
Cite

Document Files

RoleSpecificLatticeRescoringICASSP19

(14)

Subscribe

[1] David C. Atkins, Shrikanth Narayanan, "Role Specific Lattice Rescoring for Speaker Role Recognition from Speech Recognition Outputs", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4232. Accessed: Jul. 18, 2019.
@article{4232-19,
url = {http://sigport.org/4232},
author = {David C. Atkins; Shrikanth Narayanan },
publisher = {IEEE SigPort},
title = {Role Specific Lattice Rescoring for Speaker Role Recognition from Speech Recognition Outputs},
year = {2019} }
TY - EJOUR
T1 - Role Specific Lattice Rescoring for Speaker Role Recognition from Speech Recognition Outputs
AU - David C. Atkins; Shrikanth Narayanan
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4232
ER -
David C. Atkins, Shrikanth Narayanan. (2019). Role Specific Lattice Rescoring for Speaker Role Recognition from Speech Recognition Outputs. IEEE SigPort. http://sigport.org/4232
David C. Atkins, Shrikanth Narayanan, 2019. Role Specific Lattice Rescoring for Speaker Role Recognition from Speech Recognition Outputs. Available at: http://sigport.org/4232.
David C. Atkins, Shrikanth Narayanan. (2019). "Role Specific Lattice Rescoring for Speaker Role Recognition from Speech Recognition Outputs." Web.
1. David C. Atkins, Shrikanth Narayanan. Role Specific Lattice Rescoring for Speaker Role Recognition from Speech Recognition Outputs [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4232