Related papers: Multilingual Training and Cross-lingual Adaptation…

Unpaired data has shown to be beneficial for low-resource automatic speech recognition~(ASR), which can be involved in the design of hybrid models with multi-task training or language model dependent pre-training. In this work, we leverage…

Humans are adept at leveraging visual cues from lip movements for recognizing speech in adverse listening conditions. Audio-Visual Speech Recognition (AVSR) models follow similar approach to achieve robust speech recognition in noisy…

Human listeners readily adjust to unfamiliar speakers and language varieties through exposure, but do these adaptation benefits extend to state-of-the-art spoken language models? We introduce a scalable framework that allows for in-context…

We present a simple and efficient auxiliary loss function for automatic speech recognition (ASR) based on the connectionist temporal classification (CTC) objective. The proposed objective, an intermediate CTC loss, is attached to an…

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…

Only a handful of the world's languages are abundant with the resources that enable practical applications of speech processing technologies. One of the methods to overcome this problem is to use the resources existing in other languages to…

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…

Developing a unified multilingual model has long been a pursuit for machine translation. However, existing approaches suffer from performance degradation -- a single multilingual model is inferior to separately trained bilingual ones on…

A key challenge for automatic speech recognition (ASR) systems is to model the speaker level variability. In this paper, compact speaker dependent learning hidden unit contributions (LHUC) are used to facilitate both speaker adaptive…

Recent end-to-end Automatic Speech Recognition (ASR) systems demonstrated the ability to outperform conventional hybrid DNN/ HMM ASR. Aside from architectural improvements in those systems, those models grew in terms of depth, parameters…

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…

Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data. However, human annotators usually perform "non-verbatim" transcription, which can result in poorly trained models. In this paper, we…

Local dialects influence people to pronounce words of the same language differently from each other. The great variability and complex characteristics of accents creates a major challenge for training a robust and accent-agnostic automatic…

Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the…

Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by utilizing…

End-to-end ASR models trained on large amount of data tend to be implicitly biased towards language semantics of the training data. Internal language model estimation (ILME) has been proposed to mitigate this bias for autoregressive models…

This paper addresses the observed performance gap between automatic speech recognition (ASR) systems based on Long Short Term Memory (LSTM) neural networks trained with the connectionist temporal classification (CTC) loss function and…

With the recent explosion in popularity of voice assistant devices, there is a growing interest in making them available to user populations in additional countries and languages. However, to provide the highest accuracy and best…

The number of large language models (LLMs) with varying parameter scales and vocabularies is increasing. While they deliver powerful performance, they also face a set of common optimization needs to meet specific requirements or standards,…

Although connectionist temporal classification (CTC) has the label context independence assumption, it can still implicitly learn a context-dependent internal language model (ILM) due to modern powerful encoders. In this work, we…