Nathan Griot
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Nathan Griot has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Driss Matrouf
LIA, Université d'Avignon, Agroparc, BP 1228, 84911 Avignon CEDEX 9, France
1 shared publication - Mohammad MohammadAmini
LIA (Laboratoire Informatique d'Avignon University of Avignon France
1 shared publication
Latest Publications
- Open Access
Learning linguistic content embeddings for phrase and language independent utterance verification
In this paper, we introduce a phrase and language-independent utterance verification system. The objective of an utterance verification system is to confirm whether the linguistic content of two speech utterances is the same or not. Our proposed approach is phrase and language-independent, therefore it can generalize for unseen phrases and even unseen languages. The proposed framework is based on a ResNet embedding extractor trained on the Common Voice dataset which is optimized by a linguistic content classification task.The proposed approach can be used in text-dependent speaker recognition systems, passphrase verification systems, and keyword spotting systems. Our system is tested on several protocols including Deepmine for text-dependent speaker verification and Speech Commands' keyword-spotting benchmarks. Obtaining high performance for unseen phrases and languages makes our approach plausible for utterance verification in low-resource and even zero-resource languages. For example, the EER for a protocol on Common Voice English is 0.16 while for Common Voices French without using French training data the EER is 1.23.
Open AccessLearning linguistic content embeddings for phrase and language independent utterance verification
In this paper, we introduce a phrase and language-independent utterance verification system. The objective of an utterance verification system is to confirm whether the linguistic content of two speech utterances is the same or not. Our proposed approach is phrase and language-independent, therefore it can generalize for unseen phrases and even unseen languages. The proposed framework is based on a ResNet embedding extractor trained on the Common Voice dataset which is optimized by a linguistic content classification task.The proposed approach can be used in text-dependent speaker recognition systems, passphrase verification systems, and keyword spotting systems. Our system is tested on several protocols including Deepmine for text-dependent speaker verification and Speech Commands' keyword-spotting benchmarks. Obtaining high performance for unseen phrases and languages makes our approach plausible for utterance verification in low-resource and even zero-resource languages. For example, the EER for a protocol on Common Voice English is 0.16 while for Common Voices French without using French training data the EER is 1.23.