NeuralMultiling: A Novel Neural Architecture Search for Smartphone based Multilingual Speaker Verification
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913462036201472 |
|---|---|
| author | PN, Aravinda Reddy Ramachandra, Raghavendra Rao, K. Sreenivasa Mitra, Pabitra |
| author_facet | PN, Aravinda Reddy Ramachandra, Raghavendra Rao, K. Sreenivasa Mitra, Pabitra |
| contents | Multilingual speaker verification introduces the challenge of verifying a speaker in multiple languages. Existing systems were built using i-vector/x-vector approaches along with Bi-LSTMs, which were trained to discriminate speakers, irrespective of the language. Instead of exploring the design space manually, we propose a neural architecture search for multilingual speaker verification suitable for mobile devices, called \textbf{NeuralMultiling}. First, our algorithm searches for an optimal operational combination of neural cells with different architectures for normal cells and reduction cells and then derives a CNN model by stacking neural cells. Using the derived architecture, we performed two different studies:1) language agnostic condition and 2) interoperability between languages and devices on the publicly available Multilingual Audio-Visual Smartphone (MAVS) dataset. The experimental results suggest that the derived architecture significantly outperforms the existing Autospeech method by a 5-6\% reduction in the Equal Error Rate (EER) with fewer model parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04362 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | NeuralMultiling: A Novel Neural Architecture Search for Smartphone based Multilingual Speaker Verification PN, Aravinda Reddy Ramachandra, Raghavendra Rao, K. Sreenivasa Mitra, Pabitra Sound Audio and Speech Processing Multilingual speaker verification introduces the challenge of verifying a speaker in multiple languages. Existing systems were built using i-vector/x-vector approaches along with Bi-LSTMs, which were trained to discriminate speakers, irrespective of the language. Instead of exploring the design space manually, we propose a neural architecture search for multilingual speaker verification suitable for mobile devices, called \textbf{NeuralMultiling}. First, our algorithm searches for an optimal operational combination of neural cells with different architectures for normal cells and reduction cells and then derives a CNN model by stacking neural cells. Using the derived architecture, we performed two different studies:1) language agnostic condition and 2) interoperability between languages and devices on the publicly available Multilingual Audio-Visual Smartphone (MAVS) dataset. The experimental results suggest that the derived architecture significantly outperforms the existing Autospeech method by a 5-6\% reduction in the Equal Error Rate (EER) with fewer model parameters. |
| title | NeuralMultiling: A Novel Neural Architecture Search for Smartphone based Multilingual Speaker Verification |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2408.04362 |