Table 8: Cosine Similarity Between the ASR Ground-Truth and ASR Output in Application to ASR Error Correction for Baseline Pre-Trained Word2vec and the Proposed Confusion2vec: Jointly Optimized Intra-Confusion + Top-Confusion Models.

doi 10.7717/peerj-cs.195/table-8
Full Text
Abstract

Available in full text

Date

Unknown

Authors

Unknown

Publisher

PeerJ

Related search

ASR Error Segment Localization for Spoken Recovery Strategy

2013English

Figure 2: Top-Confusion2vec Training Scheme for Confusion Networks.

English

Multi-Stream ASR Trained With Heterogeneous Reverberant Environments

English

Figure 3: Proposed Intra-Confusion Training Scheme for Confusion Networks.

English

Classification and Ranking Approaches to Discriminative Language Modeling for ASR

IEEE Transactions on Audio, Speech, and Language Processing
2013English

Sir, Please Step Away From the ASR-33!

Communications of the ACM
Computer Science
2010English

Table 1: Confusion Table Associated to the Predictions by COSOPT and the Proposed Gaussian Process Approach.

English

Speech Enhancement With LSTM Recurrent Neural Networks and Its Application to Noise-Robust ASR

Lecture Notes in Computer Science
Computer ScienceTheoretical Computer Science
2015English

Efficient Codebooks for Fast and Accurate Low Resource ASR Systems

Speech Communication
LinguisticsPattern RecognitionLanguageCommunicationSimulationComputer VisionComputer Science ApplicationsModelingSoftware
2009English

Amanote Research

Note-taking for researchers

Follow Amanote

© 2024 Amaplex Software S.P.R.L. All rights reserved.

Privacy PolicyRefund Policy