Related papers: Leveraging native language information for improve…
Techniques for multi-lingual and cross-lingual speech recognition can help in low resource scenarios, to bootstrap systems and enable analysis of new languages and domains. End-to-end approaches, in particular sequence-based techniques, are…
Exploiting cross-lingual resources is an effective way to compensate for data scarcity of low resource languages. Recently, a novel multilingual model fusion technique has been proposed where a model is trained to learn cross-lingual…
Multilingual automatic lyrics transcription (ALT) is a challenging task due to the limited availability of labelled data and the challenges introduced by singing, compared to multilingual automatic speech recognition. Although some…
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…
State-of-the-art automatic speech recognition (ASR) systems struggle with the lack of data for rare accents. For sufficiently large datasets, neural engines tend to outshine statistical models in most natural language processing problems.…
In real-world applications, automatic speech recognition (ASR) systems must handle overlapping speech from multiple speakers and recognize rare words like technical terms. Traditional methods address multi-talker ASR and contextual biasing…
Recently, Large Language Models (LLMs) have shown impressive language capabilities. While most of the existing LLMs have very unbalanced performance across different languages, multilingual alignment based on translation parallel data is an…
Cross-lingual Summarization (CLS) aims at producing a summary in the target language for an article in the source language. Traditional solutions employ a two-step approach, i.e. translate then summarize or summarize then translate.…
The machine translation mechanism translates texts automatically between different natural languages, and Neural Machine Translation (NMT) has gained attention for its rational context analysis and fluent translation accuracy. However,…
We work to create a multilingual speech synthesis system which can generate speech with the proper accent while retaining the characteristics of an individual voice. This is challenging to do because it is expensive to obtain bilingual…
Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…
Acoustic-to-word (A2W) models that allow direct mapping from acoustic signals to word sequences are an appealing approach to end-to-end automatic speech recognition due to their simplicity. However, prior works have shown that modelling A2W…
Multi-task learning (MTL) and attention mechanism have been proven to effectively extract robust acoustic features for various speech-related tasks in noisy environments. In this study, we propose an attention-based MTL (ATM) approach that…
This paper describes the architecture and systems built towards solving the SemEval 2023 Task 2: MultiCoNER II (Multilingual Complex Named Entity Recognition) [1]. We evaluate two approaches (a) a traditional Conditional Random Fields model…
In recent years, self-supervised learning (SSL) models have produced promising results in a variety of speech-processing tasks, especially in contexts of data scarcity. In this paper, we study the use of SSL models for the task of…
In recent years, neural models learned through self-supervised pretraining on large scale multilingual text or speech data have exhibited promising results for underresourced languages, especially when a relatively large amount of data from…
We propose a multitask training method for attention-based end-to-end speech recognition models. We regularize the decoder in a listen, attend, and spell model by multitask training it on both audio-text and text-only data. Trained on the…
In this paper, we propose a two-phase training approach where pre-trained large language models are continually pre-trained on parallel data and then supervised fine-tuned with a small amount of high-quality parallel data. To investigate…
Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to monolingual settings and short, isolated utterances. While recent efforts in context-aware ASR…
As global demand for multilingual large language models (LLMs) grows, most LLMs still remain overly focused on English, leading to the limited access to advanced AI for non-English speakers. Current methods to enhance multilingual…