Making More of Little Data: Improving Low-Resource ASR Using Data Augmentation (ACL 2023)
Making More of Little Data: Improving Low-Resource ASR Using Data Augmentation (ACL 2023)
|
Yükleniyor...
 Hızlı erişim için Tubidy'yi favorilerinize ekleyin.
Lütfen bekleyiniz...
Type
Size

 İlgili Videolar

Making More of Little Data: Improving Low-Resource ASR Using Data Augmentation (ACL 2023)

Making More of Little Data: Improving Low-Resource ASR Using Data Augmentation (ACL 2023)

|
Low Resource German ASR with Untranscribed Data Spoken by Non-native Children - INTERSPEECH 2021...

Low Resource German ASR with Untranscribed Data Spoken by Non-native Children - INTERSPEECH 2021...

|
Reduce and Reconstruct: ASR for Low-Resource Phonetic Languages - (3 minutes introduction)

Reduce and Reconstruct: ASR for Low-Resource Phonetic Languages - (3 minutes introduction)

|
Semantic Data Augmentation for End-to-End Mandarin Speech Recognition - (3 minutes introduction)...

Semantic Data Augmentation for End-to-End Mandarin Speech Recognition - (3 minutes introduction)...

|
Defense by data augmentation

Defense by data augmentation

|
Leveraging non-target language resources to improve ASR performance in a target language - (3 mi...

Leveraging non-target language resources to improve ASR performance in a target language - (3 mi...

|
[Paper Review] Data Augmentation for Low-Resource Neural Machine Translation

[Paper Review] Data Augmentation for Low-Resource Neural Machine Translation

|
Semi-Supervision in ASR: Sequential MixMatch and Factorized TTS-Based Augmentation - (3 minutes ...

Semi-Supervision in ASR: Sequential MixMatch and Factorized TTS-Based Augmentation - (3 minutes ...

|
Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation

Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation

|
Self-Supervised Pretraining Improves Self-Supervised Pretraining

Self-Supervised Pretraining Improves Self-Supervised Pretraining

|
1st Multilingual Model Workshop - Highly-nuanced and Context-aware Data Generation approaches

1st Multilingual Model Workshop - Highly-nuanced and Context-aware Data Generation approaches

|
Copyright. All rights reserved © 2025
Rosebank, Johannesburg, South Africa

Favorilere Ekle