Single Channel Target Speaker Extraction and Recognition with Speaker Beam

@article{Delcroix2018SingleCT,
  title={Single Channel Target Speaker Extraction and Recognition with Speaker Beam},
  author={Marc Delcroix and Kateřina Žmol{\'i}kov{\'a} and Keisuke Kinoshita and Atsunori Ogawa and Tomohiro Nakatani},
  journal={2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2018},
  pages={5554-5558}
}
This paper addresses the problem of single channel speech recognition of a target speaker in a mixture of speech signals. [...] Key ResultWe also show that the latter speaker extraction network can be optimized jointly with an acoustic model to further improve ASR performance. Expand Abstract

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 25 CITATIONS

Target Speaker Extraction for Multi-Talker Speaker Verification

VIEW 14 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A Unified Framework for Neural Speech Separation and Extraction

  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
VIEW 7 EXCERPTS
CITES METHODS

Direction-Aware Speaker Beam for Multi-Channel Speaker Extraction

  • INTERSPEECH 2019
  • 2019
VIEW 5 EXCERPTS
CITES RESULTS & METHODS
HIGHLY INFLUENCED

Optimization of Speaker Extraction Neural Network with Magnitude and Temporal Spectrum Approximation Loss

  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Acoustic Modeling for Distant Multi-talker Speech Recognition with Single- and Multi-channel Branches

  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
VIEW 1 EXCERPT
CITES METHODS

All-neural Online Source Separation, Counting, and Diarization for Meeting Analysis

  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
VIEW 1 EXCERPT
CITES BACKGROUND

Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition

  • INTERSPEECH 2019
  • 2019
VIEW 3 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 26 REFERENCES

An Overview of Noise-Robust Automatic Speech Recognition

  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2014
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Context adaptive deep neural networks for fast acoustic model adaptation

  • 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2015
VIEW 5 EXCERPTS

Optimization of Speaker-Aware Multichannel Speech Extraction with ASR Criterion

  • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2018
VIEW 1 EXCERPT

Progressive Joint Modeling in Unsupervised Single-Channel Overlapped Speech Recognition

  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2018
VIEW 2 EXCERPTS

Beamnet: End-to-end training of a beamformer-supported multi-channel ASR system

  • 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2017
VIEW 1 EXCERPT

Deep attractor network for single-microphone speaker separation

  • 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2017
VIEW 1 EXCERPT

Learning speaker representation for neural network based multichannel speaker extraction

  • 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
  • 2017
VIEW 3 EXCERPTS