A real-time speech enhancement framework for multi-party meetings

Authors:
Rudy Rotili;Emanuele Principi;Stefano Squartini;Björn Schuller
Affiliations:
A3LAB, Department of Biomedics, Electronics and Telecommunications, Università Politecnica delle Marche, Ancona, Italy;A3LAB, Department of Biomedics, Electronics and Telecommunications, Università Politecnica delle Marche, Ancona, Italy;A3LAB, Department of Biomedics, Electronics and Telecommunications, Università Politecnica delle Marche, Ancona, Italy;Institute for Human-Machine Communication, Technische Universität München, Munich, Germany
Venue:
NOLISP'11 Proceedings of the 5th international conference on Advances in nonlinear speech processing
Year:
2011

Citing 8
Cited 1

Towards Semantic Analysis of Conversations: A System for the Live Identification of Speakers in Meetings

ICSC '08 Proceedings of the 2008 IEEE International Conference on Semantic Computing
Speech Dereverberation

Speech Dereverberation
Real-time joint blind speech separation and dereverberation in presence of overlapping speakers

ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part II
Robust multi-stream keyword and non-linguistic vocalization detection for computationally intelligent virtual agents

ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part II
Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge

Speech Communication
The AMI meeting corpus: a pre-announcement

MLMI'05 Proceedings of the Second international conference on Machine Learning for Multimodal Interaction
A class of frequency-domain adaptive approaches to blind multichannel identification

IEEE Transactions on Signal Processing
Estimating Dominance in Multi-Party Meetings Using Speaker Diarization

IEEE Transactions on Audio, Speech, and Language Processing

Dominance detection in a reverberated acoustic scenario

ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a real-time speech enhancement framework working in presence of multiple sources in reverberated environments. The aim is to automatically reduce the distortions introduced by room reverberation in the available distant speech signals and thus to achieve a significant improvement of speech quality for each speaker. The overall framework is composed by three cooperating blocks, each one fulfilling a specific task: speaker diarization, room-impulse response identification and speech dereverberation. In particular the speaker diarization algorithm is essential to pilot the operations performed in the other two stages in accordance with speakers' activity in the room. Extensive computer simulations have been performed by using a subset of the AMI database: Obtained results show the effectiveness of the approach.