---
_id: '33471'
abstract:
- lang: eng
  text: "The intelligibility of demodulated audio signals from analog high frequency
    transmissions, e.g., using single-sideband\r\n(SSB) modulation, can be severely
    degraded by channel distortions and/or a mismatch between modulation and demodulation
    carrier frequency. In this work a neural network (NN)-based approach for carrier
    frequency offset (CFO) estimation from demodulated SSB signals is proposed, whereby
    a task specific architecture is presented. Additionally, a simulation framework
    for SSB signals is introduced and utilized for training the NNs. The CFO estimator
    is combined with a speech enhancement network to investigate its influence on
    the enhancement performance. The NN-based system is compared to a recently proposed
    pitch tracking based approach on publicly available data from real high frequency
    transmissions. Experiments show that the NN exhibits good CFO estimation properties
    and results in significant improvements in speech intelligibility, especially
    when combined with a noise reduction network."
author:
- first_name: Jens
  full_name: Heitkämper, Jens
  id: '27643'
  last_name: Heitkämper
- first_name: Joerg
  full_name: Schmalenstroeer, Joerg
  id: '460'
  last_name: Schmalenstroeer
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Heitkämper J, Schmalenstroeer J, Haeb-Umbach R. Neural Network Based Carrier
    Frequency Offset Estimation From Speech Transmitted Over High Frequency Channels.
    In: <i>Proceedings of the 30th European Signal Processing Conference (EUSIPCO)</i>.'
  apa: Heitkämper, J., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (n.d.). Neural Network
    Based Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency
    Channels. <i>Proceedings of the 30th European Signal Processing Conference (EUSIPCO)</i>.
    30th European Signal Processing Conference (EUSIPCO), Belgrad.
  bibtex: '@inproceedings{Heitkämper_Schmalenstroeer_Haeb-Umbach, place={Belgrad},
    title={Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted
    Over High Frequency Channels}, booktitle={Proceedings of the 30th European Signal
    Processing Conference (EUSIPCO)}, author={Heitkämper, Jens and Schmalenstroeer,
    Joerg and Haeb-Umbach, Reinhold} }'
  chicago: Heitkämper, Jens, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “Neural
    Network Based Carrier Frequency Offset Estimation From Speech Transmitted Over
    High Frequency Channels.” In <i>Proceedings of the 30th European Signal Processing
    Conference (EUSIPCO)</i>. Belgrad, n.d.
  ieee: J. Heitkämper, J. Schmalenstroeer, and R. Haeb-Umbach, “Neural Network Based
    Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency
    Channels,” presented at the 30th European Signal Processing Conference (EUSIPCO),
    Belgrad.
  mla: Heitkämper, Jens, et al. “Neural Network Based Carrier Frequency Offset Estimation
    From Speech Transmitted Over High Frequency Channels.” <i>Proceedings of the 30th
    European Signal Processing Conference (EUSIPCO)</i>.
  short: 'J. Heitkämper, J. Schmalenstroeer, R. Haeb-Umbach, in: Proceedings of the
    30th European Signal Processing Conference (EUSIPCO), Belgrad, n.d.'
conference:
  end_date: 2022-09-02
  location: Belgrad
  name: 30th European Signal Processing Conference (EUSIPCO)
  start_date: 2022-08-29
date_created: 2022-09-22T10:56:13Z
date_updated: 2023-10-26T08:15:57Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: closed
  content_type: application/pdf
  creator: jensheit
  date_created: 2022-09-22T10:48:31Z
  date_updated: 2022-09-22T10:48:31Z
  file_id: '33472'
  file_name: cfo.pdf
  file_size: 1231379
  relation: main_file
  success: 1
file_date_updated: 2022-09-22T10:48:31Z
has_accepted_license: '1'
language:
- iso: eng
place: Belgrad
project:
- _id: '52'
  name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: Proceedings of the 30th European Signal Processing Conference (EUSIPCO)
publication_status: accepted
quality_controlled: '1'
status: public
title: Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted
  Over High Frequency Channels
type: conference
user_id: '460'
year: '2022'
...