Related papers: JEIT: Joint End-to-End Model and Internal Language…

The integration of Large Language Model (LLMs) blocks with Vision Transformers (ViTs) holds immense promise for vision-only tasks by leveraging the rich semantic knowledge and reasoning capabilities of LLMs. However, a fundamental challenge…

Voice Assistants such as Alexa, Siri, and Google Assistant typically use a two-stage Spoken Language Understanding pipeline; first, an Automatic Speech Recognition (ASR) component to process customer speech and generate text transcriptions,…

Sequence transducers, such as the RNN-T and the Conformer-T, are one of the most promising models of end-to-end speech recognition, especially in streaming scenarios where both latency and accuracy are important. Although various methods,…

Despite the rapid progress of end-to-end (E2E) automatic speech recognition (ASR), it has been shown that incorporating external language models (LMs) into the decoding can further improve the recognition performance of E2E ASR systems. To…

We present several methods to improve the generalisation of language identification (LID) systems to new speakers and to new domains. These methods involve Spectral augmentation, where spectrograms are masked in the frequency or time bands…

This paper introduces a novel training framework called Focused Discriminative Training (FDT) to further improve streaming word-piece end-to-end (E2E) automatic speech recognition (ASR) models trained using either CTC or an interpolation of…

MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and limiting applicability…

Recent few-shot methods, such as parameter-efficient fine-tuning (PEFT) and pattern exploiting training (PET), have achieved impressive results in label-scarce settings. However, they are difficult to employ since they are subject to high…

Large-scale auto-regressive language models pretrained on massive text have demonstrated their impressive ability to perform new natural language tasks with only a few text examples, without the need for fine-tuning. Recent studies further…

Pretrained Language Models (PLMs) store extensive knowledge within their weights, enabling them to recall vast amount of information. However, relying on this parametric knowledge brings some limitations such as outdated information or gaps…

Text-motion retrieval aims to learn a semantically aligned latent space between natural language descriptions and 3D human motion skeleton sequences, enabling bidirectional search across the two modalities. Most existing methods use a…

Transformer-based models such as BERT and E5 have significantly advanced text embedding by capturing rich contextual representations. However, many complex real-world queries require sophisticated reasoning to retrieve relevant documents…

To realize robust end-to-end Automatic Speech Recognition(E2E ASR) under radio communication condition, we propose a multitask-based method to joint train a Speech Enhancement (SE) module as the front-end and an E2E ASR model as the…

The advent of hyper-scale and general-purpose pre-trained models is shifting the paradigm of building task-specific models for target tasks. In the field of audio research, task-agnostic pre-trained models with high transferability and…

Pre-training and fine-tuning is a paradigm for alleviating the data scarcity problem in end-to-end speech translation (E2E ST). The commonplace "modality gap" between speech and text data often leads to inconsistent inputs between…

In recent years, neural machine translation (NMT) has become the dominant approach in automated translation. However, like many other deep learning approaches, NMT suffers from overfitting when the amount of training data is limited. This…

Explainability of neural network prediction is essential to understand feature importance and gain interpretable insight into neural network performance. However, explanations of neural network outcomes are mostly limited to visualization,…

Consonant and vowel reduction are often encountered in speech, which might cause performance degradation in automatic speech recognition (ASR). Our recently proposed learning strategy based on masking, Phone Masking Training (PMT),…

Recent advances in large language models (LLMs) have attracted significant interest in extending their capabilities to multimodal scenarios, particularly for speech-to-speech conversational systems. However, existing multimodal models…

A joint speech and text optimization method is proposed for hybrid transducer and attention-based encoder decoder (TAED) modeling to leverage large amounts of text corpus and enhance ASR accuracy. The joint TAED (J-TAED) is trained with…