Academic Journal
Lightweight Real-Time Recurrent Models for Speech Enhancement and Automatic Speech Recognition.
| Τίτλος: | Lightweight Real-Time Recurrent Models for Speech Enhancement and Automatic Speech Recognition. |
|---|---|
| Συγγραφείς: | Dhahbi, Sami, Saleem, Nasir, Gunawan, Teddy Surya, Bourouis, Sami, Ali, Imad, Trigui, Aymen, Algarni, Abeer D. |
| Πηγή: | International Journal of Interactive Multimedia & Artificial Intelligence; Jun2024, Vol. 8 Issue 6, p74-85, 12p |
| Θεματικοί όροι: | Automatic speech recognition, Intelligibility of speech, Speech enhancement, Artificial neural networks, Recurrent neural networks, Speech |
| Περίληψη: | Traditional recurrent neural networks (RNNs) encounter difficulty in capturing long-term temporal dependencies. However, lightweight recurrent models for speech enhancement are important to improve noisy speech, while being computationally efficient and able to capture long-term temporal dependencies efficiently. This study proposes a lightweight hourglass-shaped model for speech enhancement (SE) and automatic speech recognition (ASR). Simple recurrent units (SRU) with skip connections are implemented where attention gates are added to the skip connections, highlighting the important features and spectral regions. The model operates without relying on future information that is well-suited for real-time processing. Combined acoustic features and two training objectives are estimated. Experimental evaluations using the short time speech intelligibility (STOI), perceptual evaluation of speech quality (PESQ), and word error rates (WERs) indicate better intelligibility, perceptual quality, and word recognition rates. The composite measures further confirm the performance of residual noise and speech distortion. With the TIMIT database, the proposed model improves the STOI and PESQ by 16.21% and 0.69 (31.1%) whereas with the LibriSpeech database, the model improves STOI by 16.41% and PESQ by 0.71 (32.9%) over the noisy speech. Further, our model outperforms other deep neural networks (DNNs) in seen and unseen conditions. The ASR performance is measured using the Kaldi toolkit and achieves 15.13% WERs in noisy backgrounds. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Interactive Multimedia & Artificial Intelligence is the property of Universidad Internacional de La Rioja (UNIR) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Βάση Δεδομένων: | Complementary Index |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:edb&genre=article&issn=19891660&ISBN=&volume=8&issue=6&date=20240601&spage=74&pages=74-85&title=International Journal of Interactive Multimedia & Artificial Intelligence&atitle=Lightweight%20Real-Time%20Recurrent%20Models%20for%20Speech%20Enhancement%20and%20Automatic%20Speech%20Recognition.&aulast=Dhahbi%2C%20Sami&id=DOI:10.9781/ijimai.2024.04.003 Name: Full Text Finder (for New FTF UI) (ns324271) Category: fullText Text: Full Text Finder MouseOverText: Full Text Finder |
|---|---|
| Header | DbId: edb DbLabel: Complementary Index An: 177785890 RelevancyScore: 966 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 965.707580566406 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Lightweight Real-Time Recurrent Models for Speech Enhancement and Automatic Speech Recognition. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Dhahbi%2C+Sami%22">Dhahbi, Sami</searchLink><br /><searchLink fieldCode="AR" term="%22Saleem%2C+Nasir%22">Saleem, Nasir</searchLink><br /><searchLink fieldCode="AR" term="%22Gunawan%2C+Teddy+Surya%22">Gunawan, Teddy Surya</searchLink><br /><searchLink fieldCode="AR" term="%22Bourouis%2C+Sami%22">Bourouis, Sami</searchLink><br /><searchLink fieldCode="AR" term="%22Ali%2C+Imad%22">Ali, Imad</searchLink><br /><searchLink fieldCode="AR" term="%22Trigui%2C+Aymen%22">Trigui, Aymen</searchLink><br /><searchLink fieldCode="AR" term="%22Algarni%2C+Abeer+D%2E%22">Algarni, Abeer D.</searchLink> – Name: TitleSource Label: Source Group: Src Data: International Journal of Interactive Multimedia & Artificial Intelligence; Jun2024, Vol. 8 Issue 6, p74-85, 12p – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Automatic+speech+recognition%22">Automatic speech recognition</searchLink><br /><searchLink fieldCode="DE" term="%22Intelligibility+of+speech%22">Intelligibility of speech</searchLink><br /><searchLink fieldCode="DE" term="%22Speech+enhancement%22">Speech enhancement</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Recurrent+neural+networks%22">Recurrent neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Speech%22">Speech</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Traditional recurrent neural networks (RNNs) encounter difficulty in capturing long-term temporal dependencies. However, lightweight recurrent models for speech enhancement are important to improve noisy speech, while being computationally efficient and able to capture long-term temporal dependencies efficiently. This study proposes a lightweight hourglass-shaped model for speech enhancement (SE) and automatic speech recognition (ASR). Simple recurrent units (SRU) with skip connections are implemented where attention gates are added to the skip connections, highlighting the important features and spectral regions. The model operates without relying on future information that is well-suited for real-time processing. Combined acoustic features and two training objectives are estimated. Experimental evaluations using the short time speech intelligibility (STOI), perceptual evaluation of speech quality (PESQ), and word error rates (WERs) indicate better intelligibility, perceptual quality, and word recognition rates. The composite measures further confirm the performance of residual noise and speech distortion. With the TIMIT database, the proposed model improves the STOI and PESQ by 16.21% and 0.69 (31.1%) whereas with the LibriSpeech database, the model improves STOI by 16.41% and PESQ by 0.71 (32.9%) over the noisy speech. Further, our model outperforms other deep neural networks (DNNs) in seen and unseen conditions. The ASR performance is measured using the Kaldi toolkit and achieves 15.13% WERs in noisy backgrounds. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Group: Ab Data: <i>Copyright of International Journal of Interactive Multimedia & Artificial Intelligence is the property of Universidad Internacional de La Rioja (UNIR) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=177785890 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.9781/ijimai.2024.04.003 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 12 StartPage: 74 Subjects: – SubjectFull: Automatic speech recognition Type: general – SubjectFull: Intelligibility of speech Type: general – SubjectFull: Speech enhancement Type: general – SubjectFull: Artificial neural networks Type: general – SubjectFull: Recurrent neural networks Type: general – SubjectFull: Speech Type: general Titles: – TitleFull: Lightweight Real-Time Recurrent Models for Speech Enhancement and Automatic Speech Recognition. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Dhahbi, Sami – PersonEntity: Name: NameFull: Saleem, Nasir – PersonEntity: Name: NameFull: Gunawan, Teddy Surya – PersonEntity: Name: NameFull: Bourouis, Sami – PersonEntity: Name: NameFull: Ali, Imad – PersonEntity: Name: NameFull: Trigui, Aymen – PersonEntity: Name: NameFull: Algarni, Abeer D. IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2024 Type: published Y: 2024 Identifiers: – Type: issn-print Value: 19891660 Numbering: – Type: volume Value: 8 – Type: issue Value: 6 Titles: – TitleFull: International Journal of Interactive Multimedia & Artificial Intelligence Type: main |
| ResultId | 1 |