Enhancing LSTM RNN-Based Speech Overlap Detection by Artificially Mixed Data
@inproceedings{Hagerer2017EnhancingLR, title={Enhancing LSTM RNN-Based Speech Overlap Detection by Artificially Mixed Data}, author={Gerhard Hagerer and Vedhas Pandit and F. Eyben and B. Schuller}, booktitle={Semantic Audio}, year={2017} }
This paper presents a new method for Long Short-Term Memory Recurrent Neural Network (LSTM) based speech overlap detection. To this end, speech overlap data is created artificially by mixing large amounts of speech utterances. Our elaborate training strategies and presented network structures demonstrate performance surpassing the considered state-of-the-art overlap detectors. Thereby we target the full ternary task of non-speech, speech, and overlap detection. Furthermore, speakers’ gender is… CONTINUE READING
Figures, Tables, and Topics from this paper
12 Citations
Overlap-Aware Diarization: Resegmentation Using Neural End-to-End Overlapped Speech Detection
- Computer Science, Engineering
- ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- 2020
- 14
- PDF
CountNet: Estimating the Number of Concurrent Speakers Using Supervised Learning
- Computer Science
- IEEE/ACM Transactions on Audio, Speech, and Language Processing
- 2019
- 13
- PDF
Gender Classification Based on the Non-Lexical Cues of Emergency Calls with Recurrent Neural Networks (RNN)
- Mathematics, Computer Science
- Symmetry
- 2019
- 4
- Highly Influenced
- PDF
DOVER-Lap: A Method for Combining Overlap-aware Diarization Outputs
- Computer Science, Engineering
- ArXiv
- 2020
- 1
- PDF
Spherediar: An Effective Speaker Diarization System for Meeting Data
- Computer Science
- 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
- 2019
- 2
- Highly Influenced
- PDF
Classification vs. Regression in Supervised Learning for Single Channel Speaker Count Estimation
- Computer Science, Engineering
- 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- 2018
- 14
- PDF
Multi-class Spectral Clustering with Overlaps for Speaker Diarization
- Computer Science, Engineering
- ArXiv
- 2020
- 2
- PDF
"Did you laugh enough today?" - Deep Neural Networks for Mobile and Wearable Laughter Trackers
- Computer Science
- INTERSPEECH
- 2017
- 5
- PDF
A Paralinguistic Approach To Speaker Diarisation: Using Age, Gender, Voice Likability and Personality Traits
- Computer Science
- ACM Multimedia
- 2017
- 7
References
SHOWING 1-10 OF 28 REFERENCES
Detecting overlapping speech with long short-term memory recurrent neural networks
- Computer Science
- INTERSPEECH
- 2013
- 25
- PDF
Convolutive Non-Negative Sparse Coding and New Features for Speech Overlap Handling in Speaker Diarization
- Computer Science
- INTERSPEECH
- 2012
- 19
- PDF
The Detection of Overlapping Speech with Prosodic Features for Speaker Diarization
- Computer Science
- INTERSPEECH
- 2011
- 29
- PDF
Speech overlap detection in a two-pass speaker diarization system
- Computer Science
- INTERSPEECH
- 2009
- 27
- PDF
Speech overlap detection and attribution using convolutive non-negative sparse coding
- Computer Science
- 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- 2012
- 25
- PDF
Improved overlap speech diarization of meeting recordings using long-term conversational features
- Computer Science
- 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
- 2013
- 21
- PDF
Annotating and categorizing competition in overlap speech
- Computer Science
- 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- 2015
- 15
- PDF
Overlapped speech detection for improved speaker diarization in multiparty meetings
- Computer Science
- 2008 IEEE International Conference on Acoustics, Speech and Signal Processing
- 2008
- 98
- PDF
Speech recognition robust against speech overlapping in monaural recordings of telephone conversations
- Computer Science
- 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- 2016
- 4
- PDF