Streaming end-to-end bilingual ASR systems with joint language identiﬁcation

doi:doi:10.57702/b2f7o39e

Streaming end-to-end bilingual ASR systems with joint language identiﬁcation

Multilingual ASR technology simplifies model training and deployment, but its accuracy is known to depend on the availability of language information at runtime.

BibTex:

@dataset{Surabhi_Punjabi_and_Harish_Arsikere_and_Zeynab_Raeesy_and_Chander_Chandak_and_Nikhil_Bhave_and_Ankish_Bansal_and_Markus_M¨uller_and_Sergio_Murillo_and_Ariya_Rastrow_and_Sri_Garimella_and_Roland_Maas_and_Mat_Hans_and_Athanasios_Mouchtaris_and_Siegfried_Kunzmann_2025,
    abstract = {Multilingual ASR technology simplifies model training and deployment, but its accuracy is known to depend on the availability of language information at runtime.},
    author = {Surabhi Punjabi and Harish Arsikere and Zeynab Raeesy and Chander Chandak and Nikhil Bhave and Ankish Bansal and Markus M¨uller and Sergio Murillo and Ariya Rastrow and Sri Garimella and Roland Maas and Mat Hans and Athanasios Mouchtaris and Siegfried Kunzmann},
    doi = {10.57702/b2f7o39e},
    institution = {No Organization},
    keyword = {'Joint Language Identification', 'Multilingual ASR', 'Streaming Speech Recognition'},
    month = {jan},
    publisher = {TIB},
    title = {Streaming end-to-end bilingual ASR systems with joint language identiﬁcation},
    url = {https://service.tib.eu/ldmservice/dataset/streaming-end-to-end-bilingual-asr-systems-with-joint-language-identi-cation},
    year = {2025}
}