Related papers: CLASP: Contrastive Language-Speech Pretraining for…
Audio-text retrieval based on natural language descriptions is a challenging task. It involves learning cross-modality alignments between long sequences under inadequate data conditions. In this work, we investigate several audio features…
Contrastive language-audio pre-training (CLAP), which learns audio-language representations by aligning audio and text in a common feature space, has become popular for solving audio tasks. However, CLAP's audio features lack…
Understanding structure-property relationships is an essential yet challenging aspect of materials discovery and development. To facilitate this process, recent studies in materials informatics have sought latent embedding spaces of crystal…
Contextual-LAS (CLAS) has been shown effective in improving Automatic Speech Recognition (ASR) of rare words. It relies on phrase-level contextual modeling and attention-based relevance scoring without explicit contextual constraint which…
Contrastive language-audio pretraining (CLAP) is widely used for audio generation and recognition tasks. For example, CLAPScore, which utilizes the similarity of CLAP embeddings, has been a major metric for the evaluation of the relevance…
More than half of the 7,000 languages in the world are in imminent danger of going extinct. Traditional methods of documenting language proceed by collecting audio data followed by manual annotation by trained linguists at different levels…
Improving text representation has attracted much attention to achieve expressive text-to-speech (TTS). However, existing works only implicitly learn the prosody with masked token reconstruction tasks, which leads to low training efficiency…
Human-centric visual analysis plays a pivotal role in diverse applications, including surveillance, healthcare, and human-computer interaction. With the emergence of large-scale unlabeled human image datasets, there is an increasing need…
Learning to associate audio with textual descriptions is valuable for a range of tasks, including pretraining, zero-shot classification, audio retrieval, audio captioning, and text-conditioned audio generation. Existing contrastive…
Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings. This can be achieved by language-queried target sound extraction (TSE), which typically consists of two components: a query network that…
Language-audio joint representation learning frameworks typically depend on deterministic embeddings, assuming a one-to-one correspondence between audio and text. In real-world settings, however, the language-audio relationship is…
With the rapid development of artificial intelligence, multimodal learning has become an important research area. For intelligent agents, the state is a crucial modality to convey precise information alongside common modalities like images,…
As one of the most intuitive interfaces known to humans, natural language has the potential to mediate many tasks that involve human-computer interaction, especially in application-focused fields like Music Information Retrieval. In this…
This paper presents CLaSP, a novel model for retrieving time-series signals using natural language queries that describe signal characteristics. The ability to search time-series signals based on descriptive queries is essential in domains…
The ambiguity of human emotions poses several challenges for machine learning models, as they often overlap and lack clear delineating boundaries. Contrastive language-audio pretraining (CLAP) has emerged as a key technique for…
We propose Fast Language-Audio Pre-training (FLAP), a self-supervised approach that efficiently and effectively learns aligned audio and language representations through masking, contrastive learning and reconstruction. For efficiency, FLAP…
We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unlabeled speech and text in multiple languages. mSLAM combines…
Speech encodes paralinguistic information such as demographics, voice quality, and health. Yet no audio foundation model supports zero-shot or out-of-distribution (OOD) generalization to these tasks. We introduce SLAP (Speaker contrastive…
Self-supervised speech pre-training empowers the model with the contextual structure inherent in the speech signal while self-supervised text pre-training empowers the model with linguistic information. Both of them are beneficial for…
Multimodal processing has attracted much attention lately especially with the success of pre-training. However, the exploration has mainly focused on vision-language pre-training, as introducing more modalities can greatly complicate model…