Matches in SemOpenAlex for { <https://semopenalex.org/work/W4299617822> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W4299617822 abstract "A Pascal challenge entitled monaural multi-talker speech recognition was developed, targeting the problem of robust automatic speech recognition against speech like noises which significantly degrades the performance of automatic speech recognition systems. In this challenge, two competing speakers say a simple command simultaneously and the objective is to recognize speech of the target speaker. Surprisingly during the challenge, a team from IBM research, could achieve a performance better than human listeners on this task. The proposed method of the IBM team, consist of an intermediate speech separation and then a single-talker speech recognition. This paper reconsiders the task of this challenge based on gain adapted factorial speech processing models. It develops a joint-token passing algorithm for direct utterance decoding of both target and masker speakers, simultaneously. Comparing it to the challenge winner, it uses maximum uncertainty during the decoding which cannot be used in the past two-phased method. It provides detailed derivation of inference on these models based on general inference procedures of probabilistic graphical models. As another improvement, it uses deep neural networks for joint-speaker identification and gain estimation which makes these two steps easier than before producing competitive results for these steps. The proposed method of this work outperforms past super-human results and even the results were achieved recently by Microsoft research, using deep neural networks. It achieved 5.5% absolute task performance improvement compared to the first super-human system and 2.7% absolute task performance improvement compared to its recent competitor." @default.
- W4299617822 created "2022-10-02" @default.
- W4299617822 creator A5048230415 @default.
- W4299617822 creator A5082241781 @default.
- W4299617822 date "2016-10-05" @default.
- W4299617822 modified "2023-09-24" @default.
- W4299617822 title "Monaural Multi-Talker Speech Recognition using Factorial Speech Processing Models" @default.
- W4299617822 doi "https://doi.org/10.48550/arxiv.1610.01367" @default.
- W4299617822 hasPublicationYear "2016" @default.
- W4299617822 type Work @default.
- W4299617822 citedByCount "0" @default.
- W4299617822 crossrefType "posted-content" @default.
- W4299617822 hasAuthorship W4299617822A5048230415 @default.
- W4299617822 hasAuthorship W4299617822A5082241781 @default.
- W4299617822 hasBestOaLocation W42996178221 @default.
- W4299617822 hasConcept C102894143 @default.
- W4299617822 hasConcept C11413529 @default.
- W4299617822 hasConcept C127413603 @default.
- W4299617822 hasConcept C133892786 @default.
- W4299617822 hasConcept C154945302 @default.
- W4299617822 hasConcept C155635449 @default.
- W4299617822 hasConcept C201995342 @default.
- W4299617822 hasConcept C2776214188 @default.
- W4299617822 hasConcept C2780451532 @default.
- W4299617822 hasConcept C28490314 @default.
- W4299617822 hasConcept C41008148 @default.
- W4299617822 hasConcept C57273362 @default.
- W4299617822 hasConcept C61328038 @default.
- W4299617822 hasConceptScore W4299617822C102894143 @default.
- W4299617822 hasConceptScore W4299617822C11413529 @default.
- W4299617822 hasConceptScore W4299617822C127413603 @default.
- W4299617822 hasConceptScore W4299617822C133892786 @default.
- W4299617822 hasConceptScore W4299617822C154945302 @default.
- W4299617822 hasConceptScore W4299617822C155635449 @default.
- W4299617822 hasConceptScore W4299617822C201995342 @default.
- W4299617822 hasConceptScore W4299617822C2776214188 @default.
- W4299617822 hasConceptScore W4299617822C2780451532 @default.
- W4299617822 hasConceptScore W4299617822C28490314 @default.
- W4299617822 hasConceptScore W4299617822C41008148 @default.
- W4299617822 hasConceptScore W4299617822C57273362 @default.
- W4299617822 hasConceptScore W4299617822C61328038 @default.
- W4299617822 hasLocation W42996178221 @default.
- W4299617822 hasLocation W42996178222 @default.
- W4299617822 hasOpenAccess W4299617822 @default.
- W4299617822 hasPrimaryLocation W42996178221 @default.
- W4299617822 hasRelatedWork W1486956970 @default.
- W4299617822 hasRelatedWork W1501076695 @default.
- W4299617822 hasRelatedWork W1822699154 @default.
- W4299617822 hasRelatedWork W2111874347 @default.
- W4299617822 hasRelatedWork W2122924390 @default.
- W4299617822 hasRelatedWork W2181824266 @default.
- W4299617822 hasRelatedWork W2528813655 @default.
- W4299617822 hasRelatedWork W2573756443 @default.
- W4299617822 hasRelatedWork W4299617822 @default.
- W4299617822 hasRelatedWork W642007152 @default.
- W4299617822 isParatext "false" @default.
- W4299617822 isRetracted "false" @default.
- W4299617822 workType "article" @default.