Abstract | ||
---|---|---|
In this paper, we introduce a streaming keyphrase detection system that can be easily customized to accurately detect any phrase composed of words from a large vocabulary. The system is implemented with an end-to-end trained automatic speech recognition (ASR) model and a text-independent speaker verification model. To address the challenge of detecting these keyphrases under various noisy conditions, a speaker separation model is added to the feature frontend of the speaker verification model, and an adaptive noise cancellation (ANC) algorithm is included to exploit cross-microphone noise coherence. Our experiments show that the text-independent speaker verification model largely reduces the false triggering rate of the keyphrase detection, while the speaker separation model and adaptive noise cancellation largely reduce false rejections. |
Year | DOI | Venue |
---|---|---|
2021 | 10.21437/Interspeech.2021-204 | Interspeech |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rajeev Rikhye | 1 | 0 | 1.01 |
Quan Wang | 2 | 115 | 20.15 |
Qiao Liang | 3 | 77 | 19.86 |
Yanzhang He | 4 | 64 | 16.36 |
Ding Zhao | 5 | 0 | 3.04 |
Yiteng | 6 | 0 | 0.34 |
Huang | 7 | 2 | 2.40 |
Arun Narayanan | 8 | 425 | 32.99 |
Ian McGraw | 9 | 253 | 24.41 |