Words from spontaneous conversational speech can be recognized with human-like accuracy by an error-driven learning algorithm that discriminates between meanings straight from smart acoustic features, bypassing the phoneme as recognition unit.
Sound units play a pivotal role in cognitive models of auditory comprehension. The general consensus is that during perception listeners break down speech into auditory words and subsequently phones. Indeed, cognitive speech recognition is typically taken to be computationally intractable without ph...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2017-01-01
|
| Series: | PLoS ONE |
| Online Access: | http://europepmc.org/articles/PMC5386243?pdf=render |
| _version_ | 1818305612151259136 |
|---|---|
| author | Denis Arnold Fabian Tomaschek Konstantin Sering Florence Lopez R Harald Baayen |
| author_facet | Denis Arnold Fabian Tomaschek Konstantin Sering Florence Lopez R Harald Baayen |
| author_sort | Denis Arnold |
| collection | DOAJ |
| description | Sound units play a pivotal role in cognitive models of auditory comprehension. The general consensus is that during perception listeners break down speech into auditory words and subsequently phones. Indeed, cognitive speech recognition is typically taken to be computationally intractable without phones. Here we present a computational model trained on 20 hours of conversational speech that recognizes word meanings within the range of human performance (model 25%, native speakers 20-44%), without making use of phone or word form representations. Our model also generates successfully predictions about the speed and accuracy of human auditory comprehension. At the heart of the model is a 'wide' yet sparse two-layer artificial neural network with some hundred thousand input units representing summaries of changes in acoustic frequency bands, and proxies for lexical meanings as output units. We believe that our model holds promise for resolving longstanding theoretical problems surrounding the notion of the phone in linguistic theory. |
| first_indexed | 2024-12-13T06:29:21Z |
| format | Article |
| id | doaj.art-4cea13a2e4e6477f82225359a1679ee7 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-13T06:29:21Z |
| publishDate | 2017-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-4cea13a2e4e6477f82225359a1679ee72022-12-21T23:56:38ZengPublic Library of Science (PLoS)PLoS ONE1932-62032017-01-01124e017462310.1371/journal.pone.0174623Words from spontaneous conversational speech can be recognized with human-like accuracy by an error-driven learning algorithm that discriminates between meanings straight from smart acoustic features, bypassing the phoneme as recognition unit.Denis ArnoldFabian TomaschekKonstantin SeringFlorence LopezR Harald BaayenSound units play a pivotal role in cognitive models of auditory comprehension. The general consensus is that during perception listeners break down speech into auditory words and subsequently phones. Indeed, cognitive speech recognition is typically taken to be computationally intractable without phones. Here we present a computational model trained on 20 hours of conversational speech that recognizes word meanings within the range of human performance (model 25%, native speakers 20-44%), without making use of phone or word form representations. Our model also generates successfully predictions about the speed and accuracy of human auditory comprehension. At the heart of the model is a 'wide' yet sparse two-layer artificial neural network with some hundred thousand input units representing summaries of changes in acoustic frequency bands, and proxies for lexical meanings as output units. We believe that our model holds promise for resolving longstanding theoretical problems surrounding the notion of the phone in linguistic theory.http://europepmc.org/articles/PMC5386243?pdf=render |
| spellingShingle | Denis Arnold Fabian Tomaschek Konstantin Sering Florence Lopez R Harald Baayen Words from spontaneous conversational speech can be recognized with human-like accuracy by an error-driven learning algorithm that discriminates between meanings straight from smart acoustic features, bypassing the phoneme as recognition unit. PLoS ONE |
| title | Words from spontaneous conversational speech can be recognized with human-like accuracy by an error-driven learning algorithm that discriminates between meanings straight from smart acoustic features, bypassing the phoneme as recognition unit. |
| title_full | Words from spontaneous conversational speech can be recognized with human-like accuracy by an error-driven learning algorithm that discriminates between meanings straight from smart acoustic features, bypassing the phoneme as recognition unit. |
| title_fullStr | Words from spontaneous conversational speech can be recognized with human-like accuracy by an error-driven learning algorithm that discriminates between meanings straight from smart acoustic features, bypassing the phoneme as recognition unit. |
| title_full_unstemmed | Words from spontaneous conversational speech can be recognized with human-like accuracy by an error-driven learning algorithm that discriminates between meanings straight from smart acoustic features, bypassing the phoneme as recognition unit. |
| title_short | Words from spontaneous conversational speech can be recognized with human-like accuracy by an error-driven learning algorithm that discriminates between meanings straight from smart acoustic features, bypassing the phoneme as recognition unit. |
| title_sort | words from spontaneous conversational speech can be recognized with human like accuracy by an error driven learning algorithm that discriminates between meanings straight from smart acoustic features bypassing the phoneme as recognition unit |
| url | http://europepmc.org/articles/PMC5386243?pdf=render |
| work_keys_str_mv | AT denisarnold wordsfromspontaneousconversationalspeechcanberecognizedwithhumanlikeaccuracybyanerrordrivenlearningalgorithmthatdiscriminatesbetweenmeaningsstraightfromsmartacousticfeaturesbypassingthephonemeasrecognitionunit AT fabiantomaschek wordsfromspontaneousconversationalspeechcanberecognizedwithhumanlikeaccuracybyanerrordrivenlearningalgorithmthatdiscriminatesbetweenmeaningsstraightfromsmartacousticfeaturesbypassingthephonemeasrecognitionunit AT konstantinsering wordsfromspontaneousconversationalspeechcanberecognizedwithhumanlikeaccuracybyanerrordrivenlearningalgorithmthatdiscriminatesbetweenmeaningsstraightfromsmartacousticfeaturesbypassingthephonemeasrecognitionunit AT florencelopez wordsfromspontaneousconversationalspeechcanberecognizedwithhumanlikeaccuracybyanerrordrivenlearningalgorithmthatdiscriminatesbetweenmeaningsstraightfromsmartacousticfeaturesbypassingthephonemeasrecognitionunit AT rharaldbaayen wordsfromspontaneousconversationalspeechcanberecognizedwithhumanlikeaccuracybyanerrordrivenlearningalgorithmthatdiscriminatesbetweenmeaningsstraightfromsmartacousticfeaturesbypassingthephonemeasrecognitionunit |