相关论文: WhisBERT: Multimodal Text-Audio Language Modeling …

The prevalence of large-scale multimodal datasets presents unique challenges in assessing dataset quality. We propose a two-step method to analyze multimodal datasets, which leverages a small seed of human annotation to map each multimodal…

This work investigates the use of large-scale, English-only pre-trained models (CLIP and HuBERT) for multilingual image-speech retrieval. For non-English image-speech retrieval, we outperform the current state-of-the-art performance by a…

Multi-modal learning in the audio-language domain has seen significant advancements in recent years. However, audio-language learning faces challenges due to limited and lower-quality data compared to image-language tasks. Existing…

Multilingual speech recognition with supervised learning has achieved great results as reflected in recent research. With the development of pretraining methods on audio and text data, it is imperative to transfer the knowledge from…

Recognizing a speaker's level of commitment to a belief is a difficult task; humans do not only interpret the meaning of the words in context, but also understand cues from intonation and other aspects of the audio signal. Many papers and…

Mean Opinion Score (MOS) prediction for text to music systems requires evaluating both overall musical quality and text prompt alignment. This paper introduces WhisQ, a multimodal architecture that addresses this dual-assessment challenge…

Recently, instruction-following audio-language models have received broad attention for audio interaction with humans. However, the absence of pre-trained audio models capable of handling diverse audio types and tasks has hindered progress…

Masked Language Modeling (MLM) is widely used to pretrain language models. The standard random masking strategy in MLM causes the pre-trained language models (PLMs) to be biased toward high-frequency tokens. Representation learning of rare…

Understanding the interplay between intra-modality dependencies (the contribution of an individual modality to a target task) and inter-modality dependencies (the relationships between modalities and the target task) is fundamental to…

The emergence of large language models (LLMs) has sparked significant interest in extending their remarkable language capabilities to speech. However, modality alignment between speech and text still remains an open problem. Current…

Whisper is a multitask and multilingual speech model covering 99 languages. It yields commendable automatic speech recognition (ASR) results in a subset of its covered languages, but the model still underperforms on a non-negligible number…

Unsupervised pre-training is now the predominant approach for both text and speech understanding. Self-attention models pre-trained on large amounts of unannotated data have been hugely successful when fine-tuned on downstream tasks from a…

Joint speech-language training is challenging due to the large demand for training data and GPU consumption, as well as the modality gap between speech and language. We present ComSL, a speech-language model built atop a composite…

As deep learning models evolve, new applications and challenges are rapidly emerging. Tasks that once relied on a single modality, such as text, images, or audio, are now enriched by seamless interactions between multimodal data. These…

Pre-training speech models on large volumes of data has achieved remarkable success. OpenAI Whisper is a multilingual multitask model trained on 680k hours of supervised speech data. It generalizes well to various speech recognition and…

Dementia is a progressive neurological disorder that profoundly affects the daily lives of older adults, impairing abilities such as verbal communication and cognitive function. Early diagnosis is essential for enhancing both lifespan and…

Conditional sound separation in multi-source audio mixtures without having access to single source sound data during training is a long standing challenge. Existing mix-and-separate based methods suffer from significant performance drop…

Despite their success in a variety of NLP tasks, pre-trained language models, due to their heavy reliance on compositionality, fail in effectively capturing the meanings of multiword expressions (MWEs), especially idioms. Therefore,…

Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions. GPT-3 has shown…

Self-supervised language and audio models effectively predict brain responses to speech. However, traditional prediction models rely on linear mappings from unimodal features, despite the complex integration of auditory signals with…