Investigating zero-shot generalizability on mandarin-english code-switched asr and speech-to-text translation of recent foundation models with self-supervision and …

CK Yang, KP Huang, KH Lu, CY Kuan… - … , Speech, and Signal …, 2024 - ieeexplore.ieee.org
This work evaluated several cutting-edge large-scale foundation models based on self-
supervision or weak supervision, including SeamlessM4T, SeamlessM4T v2, and Whisper …

The Balancing Act: Unmasking and Alleviating ASR Biases in Portuguese

A Kulkarni, A Tokareva, R Qureshi… - arxiv preprint arxiv …, 2024 - arxiv.org
In the field of spoken language understanding, systems like Whisper and Multilingual
Massive Speech (MMS) have shown state-of-the-art performances. This study is dedicated …

Sc-moe: Switch conformer mixture of experts for unified streaming and non-streaming code-switching asr

S Ye, S Chen, X Hu, X Xu - arxiv preprint arxiv:2406.18021, 2024 - arxiv.org
In this work, we propose a Switch-Conformer-based MoE system named SC-MoE for unified
streaming and non-streaming code-switching (CS) automatic speech recognition (ASR) …

Analyzing code-switching scenarios in India's diverse linguistic landscape using end-to-end ASR systems with VITB-HEBiC

P Jain, A Bhowmick - Computers and Electrical Engineering, 2025 - Elsevier
Code-switching, where speakers alternate between languages within a conversation,
presents unique challenges for Automatic Speech Recognition (ASR) systems. The VITB …

A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directions

I Hamed, C Sabty, S Abdennadher, NT Vu… - arxiv preprint arxiv …, 2025 - arxiv.org
Language in the Arab world presents a complex diglossic and multilingual setting, involving
the use of Modern Standard Arabic, various dialects and sub-dialects, as well as multiple …

Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding

J Zhao, H Shi, C Cui, T Wang, H Liu, Z Ni, L Ye… - arxiv preprint arxiv …, 2024 - arxiv.org
Code-switching (CS) automatic speech recognition (ASR) faces challenges due to the
language confusion resulting from accents, auditory similarity, and seamless language …