Search

With the widespread use of automatic speaker recognition in realistic world, it suffers a lot when there is a domain mismatch, including channel, language, distance etc. Recent research studies have introduced the adversarial-learning mechanism into deep neural networks to reduce the distribution mismatch between different domains. However, they only aligned the domain distributions between the background training and evaluation data. Few focused on the diverse distribution underlying the enrol and test data. In this Letter, the authors propose a domain adversarial siamese (DAS) network trying to eliminate the domain influence on speech representation. Specifically, they feed a network with speech pairs from the same speaker. Then a domain discriminator is introduced to capture the domain consistence or difference between pairs. Final embeddings become domain-invariant and more speaker-discriminative. A cross-channel data set is sort out from NIST speaker recognition evaluation and more experiments are conducted on AISHELL-Wake-Up-1 data set. Results show that DAS performs equally effective with typical domain adversarial methods, improving results at least $10\%$10% on energy efficiency rating. Furthermore, it is proved to be more valid for scenarios such as unbalanced data amount and unknown domain, achieving relatively $11\%$11% improvements. [ABSTRACT FROM AUTHOR]

Lokoja, Nigeria is arguably one of the most multilingual communities in the world. The multilingual situation of Lokoja, North Central Nigeria is intriguingly much for its complexity and Lokoja which connects the broad geographical regions of Nigeria as a result of its centrality is resident to people of diverse multilingual backgrounds, such that a typical inhabitant can speak as many as nine Nigerian languages. In the midst of this multilingualism arises the problem of domain of influence and functions of the respective languages which the inhabitants speak and the different functions which the respective languages serve are dependent on a variety of factors which range from formality, familiarity to strict informality. However, there is sometimes role conflict as a result of multi-lingual complexity. The goal of this paper is to examine the socio-linguistic motivational differentials in the functions of the languages in contact in Lokoja, Kogi State, Nigeria. [ABSTRACT FROM AUTHOR]