Name
Abstract | ||
|---|---|---|
In topic identification (topic ID) on real-world unstructured audio, an audio instance of variable topic shifts is first broken into sequential segments, and each segment is independently classified. We first present a general purpose method for topic ID on spoken segments in low-resource languages, using a cascade of universal acoustic modeling, translation lexicons to English, and English-language topic classification. Next, instead of classifying each segment independently, we demonstrate that exploring the contextual dependencies across sequential segments can provide large improvements. In particular, we propose an attention-based contextual model which is able to leverage the contexts in a selective manner. We test both our contextual and non-contextual models on four LORELEI languages, and on all but one our attention-based contextual model significantly outperforms the context-independent models. |
Year | Venue | Keywords |
|---|---|---|
2018 | 2018 IEEE Spoken Language Technology Workshop (SLT) | Task analysis,Context modeling,Acoustics,Buildings,Data models,Training,Recurrent neural networks |
DocType | Volume | ISSN |
Conference | abs/1807.06204 | 2639-5479 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
7 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chunxi Liu | 1 | 23 | 3.28 |
| Matthew Wiesner | 2 | 0 | 0.34 |
| Shinji Watanabe | 3 | 1158 | 139.38 |
| Craig Harman | 4 | 25 | 3.90 |
| Jan Trmal | 5 | 235 | 20.91 |
| N. Dehak | 6 | 1269 | 92.64 |
| Sanjeev Khudanpur | 7 | 2155 | 202.00 |