| Presentation | 2014-02-26 Make Use of Automatic Speech Recognition Technology for Non-Native Speakers in a Conference Call Naomi YAMASHITA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The aim of our research is to support non-native speakers in an audio conference with the use of ASR technology. Previous research have demonstrated that transcripts generated by ASR improve non-native speakers' comprehension when its recognition rate surpasses a certain threshold (WER<20%). Unfortunately, due to various factors such as speech overlaps and fluctuation in speaking pitch, the chances of ASR recognition rate to surpass the criteria in real audio conferences are slim. To resolve the problem, we suggest showing the ASR output (automated transcripts) not only to the non-native speakers but also to the native speakers. By doing so, we encourage the native speakers to adapt to the ASR technology, which may possibly improve the recognition rate of its output and eventually improve the comprehension level of non-native speakers. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Automatic Speech Recognition (ASR) / Word Error Rate (WER) / Non-Native Speaker / teleconference |
| Paper # | AI2013-38 |
| Date of Issue |
| Conference Information | |
| Committee | AI |
|---|---|
| Conference Date | 2014/2/19(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Artificial Intelligence and Knowledge-Based Processing (AI) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Make Use of Automatic Speech Recognition Technology for Non-Native Speakers in a Conference Call |
| Sub Title (in English) | |
| Keyword(1) | Automatic Speech Recognition (ASR) |
| Keyword(2) | Word Error Rate (WER) |
| Keyword(3) | Non-Native Speaker |
| Keyword(4) | teleconference |
| 1st Author's Name | Naomi YAMASHITA |
| 1st Author's Affiliation | NTT Communication Science Laboratories() |
| Date | 2014-02-26 |
| Paper # | AI2013-38 |
| Volume (vol) | vol.113 |
| Number (no) | 441 |
| Page | pp.pp.- |
| #Pages | 2 |
| Date of Issue | |