IEEE ICASSP 2026 || Barcelona, Spain || 4-8 May 2026

SLP-P7: Multilingual ASR/ST Robustness & Evaluation

Poster

Tue, 5 May, 16:30 - 18:30

Location: Poster Area 27

Session Type: Poster

Session Co-Chairs: Thomas Hain, University of Sheffield and Yiteng (Arden) Huang, Meta Platforms

Track: Speech and Language Processing [SL]

SLP-P7.1: ACCLID: ACCENT-AWARE LANGUAGE IDENTIFICATION FOR ROBUST MULTILINGUAL SPEECH RECOGNITION

Rishabh Singh, CERN, Switzerland

SLP-P7.2: BBPE16: UTF-16-BASED BYTE-LEVEL BYTE-PAIR ENCODING FOR IMPROVED MULTILINGUAL SPEECH RECOGNITION

Hyunsik Kim, Haeri Kim, Munhak Lee, Kyungmin Lee, Samsung Research, Korea, Republic of

SLP-P7.3: CTC-DID: CTC-BASED ARABIC DIALECT IDENTIFICATION FOR STREAMING APPLICATIONS

Muhammad Umar Farooq, Oscar Saz, Emotech Ltd., United Kingdom of Great Britain and Northern Ireland

SLP-P7.4: ENHANCING LOW-RESOURCE SPEECH RECOGNITION WITH NON-LINEAR CROSS-LINGUAL MAPPINGS

Muhammad Umar Farooq, Thomas Hain, University of Sheffield, United Kingdom of Great Britain and Northern Ireland

SLP-P7.5: LANGUAGE-INFUSED RETRIEVAL-AUGMENTED CTC WITH ADAPTIVE SOFT-HARD GATING FOR ROBUST CODE-SWITCHING ASR

Zhichao Liang, Satoshi Nakamura, The Chinese University of Hong Kong, Shenzhen, China

SLP-P7.6: MIXTURES OF LIGHTWEIGHT ARTICULATORY EXPERTS FOR MULTILINGUAL ASR

Masato Mimura, Jaeyoung Lee, NTT, Inc., Japan; Ryo Magoshi, Tatsuya Kawahara, Kyoto University, Japan

SLP-P7.7: TOWARDS FAIR ASR FOR SECOND LANGUAGE SPEAKERS USING FAIRNESS PROMPTED FINETUNING

Monorama Swain, Johannes Kepler University Linz, Austria; Bubai Maji, IIT Kharagpur, India; Jagabandhu Mishra, University of Eastern Finland, Finland; Markus Schedl, Johannes Kepler University Linz, Austria; Anders Søgaard, University of Copenhagen, Denmark; Jesper Rindom Jensen, Aalborg University, Denmark