Abstract | ||
---|---|---|
The paper presents a study of usability of x-vectors for adaptation of automatic speech recognition (ASR) systems. X-vectors are Neural Network (NN)-based speaker embeddings recently proposed in speaker recognition (SR). They quickly replaced common i-vectors and became new state-of-the-art technique. Here, the same approach is adopted for ASR with the hope of similar outcome. All experiments were done on ASR for the latest IARPA MATERIAL evaluation running on Pashto language. Over 1% absolute improvement was observed with x-vectors over traditional i-vectors, even when the x-vector extractor was not trained on target Pashto data. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICASSP39728.2021.9414725 | 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) |
Keywords | DocType | Citations |
speech recognition, adaptation, x-vectors, data augmentation, robustness | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Martin Karafiát | 1 | 227 | 23.61 |
Karel Veselý | 2 | 154 | 14.62 |
Jan Cernocký | 3 | 1273 | 135.94 |
Jan Profant | 4 | 0 | 0.34 |
Jiri Nytra | 5 | 0 | 0.34 |
Miroslav Hlavacek | 6 | 0 | 0.34 |
Tomas Pavlicek | 7 | 0 | 0.34 |