English
Related papers

Related papers: Cross-Corpora Spoken Language Identification with …

200 papers

The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions. Since the target domain usually lacks labeled data, and domain shifts exist at…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-01 Han Zhu , Gaofeng Cheng , Jindong Wang , Wenxin Hou , Pengyuan Zhang , Yonghong Yan

Language identification (LID) is a critical step in curating multilingual LLM pretraining corpora from web crawls. While many studies on LID model training focus on collecting diverse training data to improve performance, low-resource…

Computation and Language · Computer Science 2026-03-11 Negar Foroutan , Jakhongir Saydaliev , Ye Eun Kim , Antoine Bosselut

End-to-end automatic speech recognition (ASR) usually suffers from performance degradation when applied to a new domain due to domain shift. Unsupervised domain adaptation (UDA) aims to improve the performance on the unlabeled target domain…

Computation and Language · Computer Science 2023-02-23 Jiaming Zhou , Shiwan Zhao , Ning Jiang , Guoqing Zhao , Yong Qin

Prior research indicates that LID model performance significantly declines on accented speech; however, the specific causes, extent, and characterization of these errors remain under-explored. (i) We identify a common failure mode on…

Computation and Language · Computer Science 2025-10-22 Niyati Bafna , Matthew Wiesner

In multi-label classification, machine learning encounters the challenge of domain generalization when handling tasks with distributions differing from the training data. Existing approaches primarily focus on vision object recognition and…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Yuxin Qiao , Keqin Li , Junhong Lin , Rong Wei , Chufeng Jiang , Yang Luo , Haoyu Yang

The Visual Language Model, known for its robust cross-modal capabilities, has been extensively applied in various computer vision tasks. In this paper, we explore the use of CLIP (Contrastive Language-Image Pretraining), a vision-language…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Huazhong Zhao , Lei Qi , Xin Geng

This paper presents a novel Dialect Identification (DID) system developed for the Fifth Edition of the Multi-Genre Broadcast challenge, the task of Fine-grained Arabic Dialect Identification (MGB-5 ADI Challenge). The system improves upon…

Audio and Speech Processing · Electrical Eng. & Systems 2019-12-20 Xiaoxiao Miao , Ian McLoughlin

Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training data analysis, and cross-lingual evaluation of large language models. Despite…

Computation and Language · Computer Science 2026-02-20 Clara Meister , Ahmetcan Yavuz , Pietro Lesci , Tiago Pimentel

While significant work has been done on personality recognition, the lack of multilingual datasets remains an unresolved challenge. To address this, we propose ADAM (Cross-Lingual (A)ttention (D)istillation with Personality-Guided…

Computation and Language · Computer Science 2026-04-13 Jing Jie Tan , Ban-Hoe Kwan , Danny Wee-Kiat Ng , Yan-Chai Hum , Noriyuki Kawarazaki , Kosuke Takano

Recently, hybrid systems of clustering and neural diarization models have been successfully applied in multi-party meeting analysis. However, current models always treat overlapped speaker diarization as a multi-label classification…

Sound · Computer Science 2022-11-21 Zhihao Du , Shiliang Zhang , Siqi Zheng , Zhijie Yan

Multilingual spoken dialogue systems have gained prominence in the recent past necessitating the requirement for a front-end Language Identification (LID) system. Most of the existing LID systems rely on modeling the language discriminative…

Prompt learning has emerged as a powerful paradigm for adapting vision-language models such as CLIP to downstream tasks. However, existing methods often overfit to seen data, leading to significant performance degradation when generalizing…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Niloufar Alipour Talemi , Hossein Kashiani , Hossein R. Nowdeh , Fatemeh Afghah

Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting under continuously evolving and imbalanced…

Artificial Intelligence · Computer Science 2026-03-24 Xi Wang , Xu Yang , Donghao Sun , Cheng Deng

State-of-the-art speaker recognition systems are trained with a large amount of human-labeled training data set. Such a training set is usually composed of various data sources to enhance the modeling capability of models. However, in…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-03 Rongjin Li , Weibin Zhang , Dongpeng Chen

Domain classification is the task of mapping spoken language utterances to one of the natural language understanding domains in intelligent personal digital assistants (IPDAs). This is a major component in mainstream IPDAs in industry.…

Machine Learning · Computer Science 2019-05-06 Han Li , Jihwan Lee , Sidharth Mudgal , Ruhi Sarikaya , Young-Bum Kim

In this paper, we explore the task of mapping spoken language utterances to one of thousands of natural language understanding domains in intelligent personal digital assistants (IPDAs). This scenario is observed for many mainstream IPDAs…

Computation and Language · Computer Science 2018-04-24 Young-Bum Kim , Dongchan Kim , Anjishnu Kumar , Ruhi Sarikaya

Training acoustic models with sequentially incoming data -- while both leveraging new data and avoiding the forgetting effect-- is an essential obstacle to achieving human intelligence level in speech recognition. An obvious approach to…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-02 Shahram Ghorbani , Soheil Khorram , John H. L. Hansen

Existing data augmentation approaches for neural machine translation (NMT) have predominantly relied on back-translating in-domain (IND) monolingual corpora. These methods suffer from issues associated with a domain information gap, which…

Computation and Language · Computer Science 2020-04-07 Wei Peng , Chongxuan Huang , Tianhao Li , Yun Chen , Qun Liu

Language models (LMs) have been instrumental for the rapid advance of natural language processing. This paper studies continual pre-training of LMs, in particular, continual domain-adaptive pre-training (or continual DAP-training). Existing…

Computation and Language · Computer Science 2023-04-13 Zixuan Ke , Yijia Shao , Haowei Lin , Tatsuya Konishi , Gyuhak Kim , Bing Liu

In recent years, supervised approaches using deep neural networks (DNNs) have become the mainstream for speech enhancement. It has been established that DNNs generalize well to untrained noises and speakers if trained using a large number…

Sound · Computer Science 2020-08-11 Ashutosh Pandey , DeLiang Wang