Related papers: Curriculum optimization for low-resource speech re…

Automatic speech recognition systems have undoubtedly advanced with the integration of multilingual and multitask models such as Whisper, which have shown a promising ability to understand and process speech across a wide range of…

Automatic Speech Scoring (ASS) is the computer-assisted evaluation of a candidate's speaking proficiency in a language. ASS systems face many challenges like open grammar, variable pronunciations, and unstructured or semi-structured…

Speech emotion recognition (SER) systems often struggle in real-world environments, where ambient noise severely degrades their performance. This paper explores a novel approach that exploits prior knowledge of testing environments to…

Speech recognition systems have achieved high recognition performance for several tasks. However, the performance of such systems is dependent on the tremendously costly development work of preparing vast amounts of task-matched transcribed…

Contextual biasing is an important and challenging task for end-to-end automatic speech recognition (ASR) systems, which aims to achieve better recognition performance by biasing the ASR system to particular context phrases such as person…

Most spoken language understanding systems use a pipeline approach composed of an automatic speech recognition interface and a natural language understanding module. This approach forces hard decisions when converting continuous inputs into…

Back-translation (BT) has become one of the de facto components in unsupervised neural machine translation (UNMT), and it explicitly makes UNMT have translation ability. However, all the pseudo bi-texts generated by BT are treated equally…

Cross-modal text-molecule retrieval task bridges molecule structures and natural language descriptions. Existing methods predominantly focus on aligning text modality and molecule modality, yet they overlook adaptively adjusting the…

It's challenging to customize transducer-based automatic speech recognition (ASR) system with context information which is dynamic and unavailable during model training. In this work, we introduce a light-weight contextual spelling…

We present our experiments in training robust to noise an end-to-end automatic speech recognition (ASR) model using intensive data augmentation. We explore the efficacy of fine-tuning a pre-trained model to improve noise robustness, and we…

We consider the problem of making efficient use of heterogeneous training data in neural machine translation (NMT). Specifically, given a training dataset with a sentence-level feature such as noise, we seek an optimal curriculum, or order…

Scores from traditional confidence classifiers (CCs) in automatic speech recognition (ASR) systems lack universal interpretation and vary with updates to the underlying confidence or acoustic models (AMs). In this work, we build…

Manually labeled corpora are expensive to create and often not available for low-resource languages or domains. Automatic labeling approaches are an alternative way to obtain labeled data in a quicker and cheaper way. However, these labels…

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

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…

Current state-of-the-art NMT systems use large neural networks that are not only slow to train, but also often require many heuristics and optimization tricks, such as specialized learning rate schedules and large batch sizes. This is…

Traditionally, research in automated speech recognition has focused on local-first encoding of audio representations to predict the spoken phonemes in an utterance. Unfortunately, approaches relying on such hyper-local information tend to…

We introduce a new unsupervised task, spoken language modeling: the learning of linguistic representations from raw audio signals without any labels, along with the Zero Resource Speech Benchmark 2021: a suite of 4 black-box, zero-shot…

Machine hearing or listening represents an emerging area. Conventional approaches rely on the design of handcrafted features specialized to a specific audio task and that can hardly generalized to other audio fields. For example,…

One of the most difficult speech recognition tasks is accurate recognition of human to human communication. Advances in deep learning over the last few years have produced major speech recognition improvements on the representative…