paper-with-me

홈 › Papers

Server-side Rescoring of Spoken Entity-centric Knowledge Queries for Virtual Assistants

2023-11-02 · Youyuan Zhang, Sashank Gondala, Thiago Fraga-Silva, Christophe Van Gysel

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-side rescoring of spoken information domain queries using various categories of Language Models (LMs) (N-gram word LMs, sub-word neural LMs). We investigate the combination of on-device and server-side signals, and demonstrate significant WER improvements of 23%-35% on various entity-centric query subpopulations by integrating various server-side LMs compared to performing ASR on-device only. We also perform a comparison between LMs trained on domain data and a GPT-3 variant offered by OpenAI as a baseline. Furthermore, we also show that model fusion of multiple server-side LMs trained from scratch most effectively combines complementary strengths of each model and integrates knowledge learned from domain-specific data to a VA ASR system.

📄 PDF Abstract BibTeX arXiv:2311.01398

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
Multi-Head Attention 설명 없음
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Lattention: Lattice-attention in ASR rescoring

2021-11-19 · Prabhat Pandey, Sergio Duarte Torres, Ali Orkan Bayer, Ankur Gandhe 외

Lattices form a compact representation of multiple hypotheses generated from an automatic speech recognition system and have been shown to improve performance of downstream tasks like spoken language understanding and sp…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognition+3

Speech Recognition Rescoring with Large Speech-Text Foundation Models

2024-09-25 · Prashanth Gurunath Shivakumar, Jari Kolehmainen, Aditya Gourav, Yi Gu 외

Large language models (LLM) have demonstrated the ability to understand human language by leveraging large amount of text data. Automatic speech recognition (ASR) systems are often limited by available transcribed speech…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+2

Privacy Preserving for Medical Image Analysis via Non-Linear Deformation Proxy

2020-11-25 · Bach Ngoc Kim, Jose Dolz, Christian Desrosiers, Pierre-Marc Jodoin

We propose a client-server system which allows for the analysis of multi-centric medical images while preserving patient identity. In our approach, the client protects the patient identity by applying a pseudo-random non…

Brain SegmentationMedical Image AnalysisPrivacy PreservingSegmentation

Space-Efficient Representation of Entity-centric Query Language Models

2022-06-29 · Christophe Van Gysel, Mirko Hannemann, Ernest Pusateri, Youssef Oualil 외

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 nam…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

AppTek's Submission to the IWSLT 2022 Isometric Spoken Language Translation Task

2022-05-12 · Patrick Wilken, Evgeny Matusov

To participate in the Isometric Spoken Language Translation Task of the IWSLT 2022 evaluation, constrained condition, AppTek developed neural Transformer-based systems for English-to-German with various mechanisms of len…

SentenceTranslation