Speech2phone: A Novel And Efficient Method For Training Speaker Recognition Models

Abstract

In this paper we present an efficient method for training models for speaker recognition using small or under-resourced datasets. This method requires less data than other SOTA (State-Of-The-Art) methods, e.g. the Angular Prototypical and GE2E loss functions, while achieving similar results to those methods. This is done using the knowledge of the reconstruction of a phoneme in the speaker's voice. For this purpose, a new dataset was built, composed of 40 male speakers, who read sentences in Portuguese, totaling approximately 3h. We compare the three best architectures trained using our method to select the best one, which is the one with a shallow architecture. Then, we compared this model with the SOTA method for the speaker recognition task: the Fast ResNet-34 trained with approximately 2,000 hours, using the loss functions Angular Prototypical and GE2E. Three experiments were carried out with datasets in different languages. Among these three experiments, our model achieved the sec

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keycasanova2020speech2phone

Related papers

• Large-scale Learning Of Generalised Representations For Speaker Recognition (2022)0.00
• Training Speaker Recognition Systems With Limited Data (2022)8.13
• Bertphone: Phonetically-aware Encoder Representations For Utterance-level Speaker And Language Recognition (2019)13.27
• Obovox Far Field Speaker Recognition: A Novel Data Augmentation Approach With Pretrained Models (2024)0.00
• Small Footprint Text-independent Speaker Verification For Embedded Systems (2020)7.16
• Less Is More: Accurate Speech Recognition & Translation Without Web-scale Data (2024)0.00
• What Shall We Do With An Hour Of Data? Speech Recognition For The Un- And Under-served Languages Of Common Voice (2021)0.00
• 3S-TSE: Efficient Three-stage Target Speaker Extraction For Real-time And Low-resource Applications (2023)5.24