Abstract
To elucidate the processes by which automatic speech recognition (ASR) architectures reach transcription decisions, our study compared human and ASR responses to stimuli with manipulated cues for stop manner (burst, silence, and vocalic onset) and voicing (voice onset time, aspiration amplitude, and vocalic onset). Fourteen participants and two ASR systems completed a forced-response identification task. Results indicated that the cues were of perceptual significance for human participants, and though weighted differently, significant predictors of ASR output. This demonstrated that ASR systems may be relying on the same key acoustic information as do human listeners for phonemic classification.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the Eighteenth Australasian International Conference on Speech Science and Technology |
| Place of Publication | Canberra, Australia |
| Publisher | The Australasian Speech Science and Technology Association, Inc. |
| Pages | 41-45 |
| Publication status | Published - 2022 |
| Event | 18th Australasian International Conference on Speech Science and Technology - Canberra, Australia Duration: 13 Dec 2022 → 16 Dec 2022 https://sst2022.com/proceedings/ |
Conference
| Conference | 18th Australasian International Conference on Speech Science and Technology |
|---|---|
| Abbreviated title | SST2022 |
| Country/Territory | Australia |
| City | Canberra |
| Period | 13/12/22 → 16/12/22 |
| Other | The Australasian Speech Science and Technology Association and the Australian National University are pleased to host the 18th Australasian International Conference on Speech Science and Technology (SST2022). SST is an international interdisciplinary conference designed to foster collaboration among speech scientists, engineers, psycholinguists, audiologists, linguists, speech/language pathologists and industrial partners, and welcomes submissions from all areas of speech science and technology. |
| Internet address |