ISCA Archive Interspeech 2014
ISCA Archive Interspeech 2014

Automatic speech recognition with primarily temporal envelope information

Payton Lin, Fei Chen, Syu Siang Wang, Ying-Hui Lai, Yu Tsao

The aim of this study is to devise a computational method to predict cochlear implant (CI) speech recognition. Here, we describe a high-throughput screening system for optimizing CI speech processing strategies using hidden Markov model (HMM)-based automatic speech recognition (ASR). Word accuracy was computed on vocoded CI speech synthesized from primarily multi-channel temporal envelope information. The ASR performance increased with the number of channels in a similar manner displayed in human recognition scores. Results showed the computational method of HMM-based ASR offers better process control for comparing signal carrier type. Training-test mismatch reduction provided a novel platform for reevaluating the relative contributions of spectral and temporal cues to human speech recognition.


doi: 10.21437/Interspeech.2014-119

Cite as: Lin, P., Chen, F., Wang, S.S., Lai, Y.-H., Tsao, Y. (2014) Automatic speech recognition with primarily temporal envelope information. Proc. Interspeech 2014, 476-480, doi: 10.21437/Interspeech.2014-119

@inproceedings{lin14_interspeech,
  author={Payton Lin and Fei Chen and Syu Siang Wang and Ying-Hui Lai and Yu Tsao},
  title={{Automatic speech recognition with primarily temporal envelope information}},
  year=2014,
  booktitle={Proc. Interspeech 2014},
  pages={476--480},
  doi={10.21437/Interspeech.2014-119},
  issn={2308-457X}
}