Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Zhu, Jiedan"'
Publikováno v:
Findings of EMNLP 2022 short
Recently, there has been an increasing interest in two-pass streaming end-to-end speech recognition (ASR) that incorporates a 2nd-pass rescoring model on top of the conventional 1st-pass streaming ASR model to improve recognition accuracy while keepi
Externí odkaz:
http://arxiv.org/abs/2211.00174
Autor:
Liang, Dawei, Su, Hang, Singh, Tarun, Mahadeokar, Jay, Puri, Shanil, Zhu, Jiedan, Thomaz, Edison, Seltzer, Mike
Interactive voice assistants have been widely used as input interfaces in various scenarios, e.g. on smart homes devices, wearables and on AR devices. Detecting the end of a speech query, i.e. speech end-pointing, is an important task for voice assis
Externí odkaz:
http://arxiv.org/abs/2210.14252
Autor:
Mahadeokar, Jay, Shi, Yangyang, Li, Ke, Le, Duc, Zhu, Jiedan, Chandra, Vikas, Kalinli, Ozlem, Seltzer, Michael L
Streaming ASR with strict latency constraints is required in many speech recognition applications. In order to achieve the required latency, streaming ASR models sacrifice accuracy compared to non-streaming ASR models due to lack of future input cont
Externí odkaz:
http://arxiv.org/abs/2203.15773
We propose a two-layer cache mechanism to speed up dynamic WFST decoding with personalized language models. The first layer is a public cache that stores most of the static part of the graph. This is shared globally among all users. A second layer is
Externí odkaz:
http://arxiv.org/abs/1910.10670
Autor:
Zhu, Jiedan
Cloud Computing systems provide a variety of storage and computation resources.One advantage is the pay-as-you-go model, where users only pay the fee for theamount of resource they have used. There could be some user-specific concerns suchas a time c
Externí odkaz:
http://rave.ohiolink.edu/etdc/view?acc_num=osu1310758418
Publikováno v:
Proceedings of the 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage & Analysis; 11/13/2010, p1-12, 12p
