Related papers: Monolingual Data Selection Analysis for English-Ma…

Code-switching (CS) poses a significant challenge for Large Language Models (LLMs), yet its comprehensibility remains underexplored in LLMs. We introduce CS-Sum, to evaluate the comprehensibility of CS by the LLMs through CS dialogue to…

Multilingual speakers tend to alternate between languages within a conversation, a phenomenon referred to as "code-switching" (CS). CS is a complex phenomenon that not only encompasses linguistic challenges, but also contains a great deal…

Prior work has proved that Translation memory (TM) can boost the performance of Neural Machine Translation (NMT). In contrast to existing work that uses bilingual corpus as TM and employs source-side similarity search for memory retrieval,…

The advancement of multimodal large language models has accelerated the development of speech-to-speech interaction systems. While natural monolingual interaction has been achieved, we find existing models exhibit deficiencies in language…

Call Centers have huge amount of audio data which can be used for achieving valuable business insights and transcription of phone calls is manually tedious task. An effective Automated Speech Recognition system can accurately transcribe…

Multilingual automatic speech recognition (ASR) systems have garnered attention for their potential to extend language coverage globally. While self-supervised learning (SSL) models, like MMS, have demonstrated their effectiveness in…

This paper introduces a set of English translations for a 123-hour subset of the CallHome Mandarin Chinese data and the HKUST Mandarin Telephone Speech data for the task of speech translation. Paired source-language speech and…

This paper details the experimental results of adapting the OpenAI's Whisper model for Code-Switch Mandarin-English Speech Recognition (ASR) on the SEAME and ASRU2019 corpora. We conducted 2 experiments: a) using adaptation data from 1 to…

This paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based…

This paper considers the unsupervised domain adaptation problem for neural machine translation (NMT), where we assume the access to only monolingual text in either the source or target language in the new domain. We propose a cross-lingual…

Semi-supervised learning (SSL) is an active area of research which aims to utilize unlabelled data in order to improve the accuracy of speech recognition systems. The current study proposes a methodology for integration of two key ideas: 1)…

Speaker-attributed automatic speech recognition (SA-ASR) in multi-party meeting scenarios is one of the most valuable and challenging ASR task. It was shown that single-channel frame-level diarization with serialized output training…

Code-switching is a data augmentation scheme mixing words from multiple languages into source lingual text. It has achieved considerable generalization performance of cross-lingual transfer tasks by aligning cross-lingual contextual word…

Although Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, the majority of the world's languages do not have usable systems due to the lack of large speech datasets to train these models.…

As a special machine translation task, dialect translation has two main characteristics: 1) lack of parallel training corpus; and 2) possessing similar grammar between two sides of the translation. In this paper, we investigate how to…

Recently, the end-to-end training approach for neural beamformer-supported multi-channel ASR has shown its effectiveness in multi-channel speech recognition. However, the integration of multiple modules makes it more difficult to perform…

Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resource scenarios. One solution to tackle this issue is to…

Many language pairs are low resource, meaning the amount and/or quality of available parallel data is not sufficient to train a neural machine translation (NMT) model which can reach an acceptable standard of accuracy. Many works have…

We present our first efforts towards building a single multilingual automatic speech recognition (ASR) system that can process code-switching (CS) speech in five languages spoken within the same population. This contrasts with related prior…

Modeling unit and model architecture are two key factors of Recurrent Neural Network Transducer (RNN-T) in end-to-end speech recognition. To improve the performance of RNN-T for Mandarin speech recognition task, a novel transformer…