Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Van Gysel, Christophe"'
Autor:
Lei, Zhihong, Na, Xingyu, Xu, Mingbin, Pusateri, Ernest, Van Gysel, Christophe, Zhang, Yuanyuan, Han, Shiyi, Huang, Zhen
Large language models (LLMs) have shown superb capability of modeling multimodal signals including audio and text, allowing the model to generate spoken or textual response given a speech input. However, it remains a challenge for the model to recogn
Externí odkaz:
http://arxiv.org/abs/2409.15353
Voice assistants increasingly use on-device Automatic Speech Recognition (ASR) to ensure speed and privacy. However, due to resource constraints on the device, queries pertaining to complex information domains often require further processing by a se
Externí odkaz:
http://arxiv.org/abs/2406.08207
Virtual Assistants (VAs) are important Information Retrieval platforms that help users accomplish various tasks through spoken commands. The speech recognition system (speech-to-text) uses query priors, trained solely on text, to distinguish between
Externí odkaz:
http://arxiv.org/abs/2406.06729
On-device Virtual Assistants (VAs) powered by Automatic Speech Recognition (ASR) require effective knowledge integration for the challenging entity-rich query recognition. In this paper, we conduct an empirical study of modeling strategies for server
Externí odkaz:
http://arxiv.org/abs/2311.01398
Autor:
Van Gysel, Christophe
Virtual assistants are becoming increasingly important speech-driven Information Retrieval platforms that assist users with various tasks. We discuss open problems and challenges with respect to modeling spoken information queries for virtual assista
Externí odkaz:
http://arxiv.org/abs/2304.13149
Virtual assistants make use of automatic speech recognition (ASR) to help users answer entity-centric queries. However, spoken entity recognition is a difficult problem, due to the large number of frequently-changing named entities. In addition, reso
Externí odkaz:
http://arxiv.org/abs/2206.14885
High-quality automatic speech recognition (ASR) is essential for virtual assistants (VAs) to work well. However, ASR often performs poorly on VA requests containing named entities. In this work, we start from the observation that many ASR errors on n
Externí odkaz:
http://arxiv.org/abs/2106.11292
Language models (LMs) for virtual assistants (VAs) are typically trained on large amounts of data, resulting in prohibitively large models which require excessive memory and/or cannot be used to serve user requests in real-time. Entropy pruning resul
Externí odkaz:
http://arxiv.org/abs/2102.07219
We focus on improving the effectiveness of a Virtual Assistant (VA) in recognizing emerging entities in spoken queries. We introduce a method that uses historical user interactions to forecast which entities will gain in popularity and become trendin
Externí odkaz:
http://arxiv.org/abs/2005.12816
Autor:
Pusateri, Ernest, Van Gysel, Christophe, Botros, Rami, Badaskar, Sameer, Hannemann, Mirko, Oualil, Youssef, Oparin, Ilya
In this work, we uncover a theoretical connection between two language model interpolation techniques, count merging and Bayesian interpolation. We compare these techniques as well as linear interpolation in three scenarios with abundant training dat
Externí odkaz:
http://arxiv.org/abs/1908.09738