no code implementations • loresmt (COLING) 2022 • Amartya Chowdhury, Deepak K. T., Samudra Vijaya K, S. R. Mahadeva Prasanna
The implementation and performance of the English-Lambani MT system are discussed in this paper.
no code implementations • 21 Aug 2023 • Jagabandhu Mishra, S. R. Mahadeva Prasanna
The initial exploration with synthetic TTSF-LD dataset shows, using x-vector as implicit language representation with appropriate analysis window length ($N$) can able to achieve at per performance with explicit LD.
no code implementations • 22 Jun 2023 • Jagabandhu Mishra, Amartya Chowdhury, S. R. Mahadeva Prasanna
Phonotactic approaches mostly use explicit way of language modeling, hence requiring intermediate phoneme modeling and transcribed data.
no code implementations • 26 Feb 2023 • Jagabandhu Mishra, Mrinmoy Bhattacharjee, S. R. Mahadeva Prasanna
With this motivation, the Indic- Multilingual Speaker Verification (I-MSV) Challenge 2022 has been designed for understanding and comparing the state-of-the-art SV techniques.
no code implementations • 10 Feb 2023 • Jagabandhu Mishra, S. R. Mahadeva Prasanna
Initially, both LCD and SCD are performed by humans.
no code implementations • 5 Mar 2022 • Jagabandhu Mishra, S. R. Mahadeva Prasanna
Spoken language change detection (LCD) refers to detecting language switching points in a multilingual speech signal.
no code implementations • 2 Oct 2021 • Protima Nomo Sudro, Rohan Kumar Das, Rohit Sinha, S. R. Mahadeva Prasanna
The automatic recognition of pathological speech, particularly from children with any articulatory impairment, is a challenging task due to various reasons.