Related papers: PolyIPA -- Multilingual Phoneme-to-Grapheme Conver…
As an indispensable ingredient of computer-assisted pronunciation training (CAPT), automatic pronunciation assessment (APA) plays a pivotal role in aiding self-directed language learners by providing multi-aspect and timely feedback.…
Nowadays voice search for points of interest (POI) is becoming increasingly popular. However, speech recognition for local POI has remained to be a challenge due to multi-dialect and massive POI. This paper improves speech recognition…
Training automatic speech recognition (ASR) systems requires large amounts of data in the target language in order to achieve good performance. Whereas large training corpora are readily available for languages like English, there exists a…
This paper develops an ensemble method for fine-tuning a language model to multiple datasets. Existing methods, such as quantized LoRA (QLoRA), are efficient when adapting to a single dataset. When training on multiple datasets of different…
The Interspeech 2025 URGENT Challenge aimed to advance universal, robust, and generalizable speech enhancement by unifying speech enhancement tasks across a wide variety of conditions, including seven different distortion types and five…
We study sample-efficient molecular optimization under a limited budget of oracle evaluations. We propose MolLIBRA (MultimOdaLity and Language Integrated Bayesian and evolutionaRy optimizAtion), a genetic algorithm based framework that…
Recent advancements in morpheme segmentation primarily emphasize word-level segmentation, often neglecting the contextual relevance within the sentence. In this study, we redefine the morpheme segmentation task as a sequence-to-sequence…
This paper examines how linguistic similarity affects cross-lingual phonetic representation in speech processing for low-resource languages, emphasizing effective source language selection. Previous cross-lingual research has used various…
Recent studies have exhibited remarkable capabilities of pre-trained multilingual Transformers, especially cross-lingual transferability. However, current methods do not measure cross-lingual transferability well, hindering the…
In the field of multimodal medical data analysis, leveraging diverse types of data and understanding their hidden relationships continues to be a research focus. The main challenges lie in effectively modeling the complex interactions…
Image2Speech is the relatively new task of generating a spoken description of an image. This paper presents an investigation into the evaluation of this task. For this, first an Image2Speech system was implemented which generates image…
A Pascal challenge entitled monaural multi-talker speech recognition was developed, targeting the problem of robust automatic speech recognition against speech like noises which significantly degrades the performance of automatic speech…
Charts are a universally adopted medium for data communication, yet existing chart understanding benchmarks are overwhelmingly English-centric, limiting their accessibility and relevance to global audiences. To address this limitation, we…
There exist three approaches for multilingual and crosslingual automatic speech recognition (MCL-ASR) - supervised pretraining with phonetic or graphemic transcription, and self-supervised pretraining. We find that pretraining with phonetic…
Contrastive Language-Image Pre-training (CLIP) relies on Vision Transformers whose attention mechanism is susceptible to spurious correlations, and scales quadratically with resolution. To address these limitations, We present CLIMP, the…
Recovering the masked speech frames is widely applied in speech representation learning. However, most of these models use random masking in the pre-training. In this work, we proposed two kinds of masking approaches: (1) speech-level…
Recently, large-scale Vision and Language (V\&L) pretraining has become the standard backbone of many multimedia systems. While it has shown remarkable performance even in unseen situations, it often performs in ways not intuitive to…
Recent vision-language models (VLMs) such as CLIP, OpenCLIP, EVA02-CLIP and SigLIP achieve strong zero-shot performance, but it is unclear how reliably they respond to controlled linguistic perturbations. We introduce Language-Guided…
A novel, generic scheme for off-line handwritten English alphabets character images is proposed. The advantage of the technique is that it can be applied in a generic manner to different applications and is expected to perform better in…
Matching place names across writing systems is a persistent obstacle to the integration of multilingual geographic sources, whether modern gazetteers, medieval itineraries, or colonial-era surveys. Existing approaches depend on…