Transfer learning from High-Resource to Low-Resource Language Improves Speech Affect Recognition Classification Accuracy

03/04/2021

∙

Speech Affect Recognition is a problem of extracting emotional affects from audio data. Low resource languages corpora are rear and affect recognition is a difficult task in cross-corpus settings. We present an approach in which the model is trained on high resource language and fine-tune to recognize affects in low resource language. We train the model in same corpus setting on SAVEE, EMOVO, Urdu, and IEMOCAP by achieving baseline accuracy of 60.45, 68.05, 80.34, and 56.58 percent respectively. For capturing the diversity of affects in languages cross-corpus evaluations are discussed in detail. We find that accuracy improves by adding the domain target data into the training data. Finally, we show that performance is improved for low resource language speech affect recognition by achieving the UAR OF 69.32 and 68.2 for Urdu and Italian speech affects.

READ FULL TEXT

Transfer learning from High-Resource to Low-Resource Language Improves Speech Affect Recognition Classification Accuracy

Transfer Learning based Speech Affect Recognition in Urdu

An Ultra Lightweight CNN for Low Resource Circuit Component Recognition

Multilingual Speech Recognition with Corpus Relatedness Sampling

Semi-supervised transfer learning for language expansion of end-to-end speech recognition models to low-resource languages

Leveraging translations for speech transcription in low-resource settings

Semi-supervised and Transfer learning approaches for low resource sentiment classification

Using Radio Archives for Low-Resource Speech Recognition: Towards an Intelligent Virtual Assistant for Illiterate Users

Transfer learning from High-Resource to Low-Resource Language Improves Speech Affect Recognition Classification Accuracy

Related Research

Transfer Learning based Speech Affect Recognition in Urdu

An Ultra Lightweight CNN for Low Resource Circuit Component Recognition

Multilingual Speech Recognition with Corpus Relatedness Sampling

Semi-supervised transfer learning for language expansion of end-to-end speech recognition models to low-resource languages

Leveraging translations for speech transcription in low-resource settings

Semi-supervised and Transfer learning approaches for low resource sentiment classification

Using Radio Archives for Low-Resource Speech Recognition: Towards an Intelligent Virtual Assistant for Illiterate Users