Extraction of Speech Transmission Index from Speech Signals Using Artificial Neural Networks

Cox T, Li F. Extraction of Speech Transmission Index from Speech Signals Using Artificial Neural Networks. In: AES Convention 110. Audio Engineering Society; 2001. Paper 5354. Available from: https://aes.org/publications/elibrary-page/?id=9990

@inproceedings{Cox2001_9990,
  author = {Cox, Trevor and Li, Francis},
  title = {{Extraction of Speech Transmission Index from Speech Signals Using Artificial Neural Networks}},
  booktitle = {AES Convention 110},
  note = {Paper 5354},
  year = {2001},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=9990}
}

TY  - CPAPER
TI  - Extraction of Speech Transmission Index from Speech Signals Using Artificial Neural Networks
AU  - Cox, Trevor
AU  - Li, Francis
T2  - AES Convention 110
M1  - Paper 5354
PY  - 2001
DA  - 2001/05/06
UR  - https://aes.org/publications/elibrary-page/?id=9990
PB  - Audio Engineering Society
LA  - en
AB  - This paper presents a novel method to extract Speech Transmission Index (STI) from reverberated speech utterances using an artificial neural network. The convolutions of anechoic speech signals and simulated impulse responses of rooms of various kinds are used to train the artificial neural network. A time to frequency domain transformation algorithm is proposed as the pre-processor. A multi-layered feed forward neural network trained by back-propagation is adopted. Once trained, the neural network can accurately estimate Speech Transmission Index from speech signals received by a microphone in rooms. This approach utilises a naturalistic sound source, speech, and hence has potential to facilitate occupied measurement.
ER  -