English
Related papers

Related papers: Natural Language Supervision for General-Purpose A…

200 papers

We report on adaptation of multilingual end-to-end speech recognition models trained on as many as 100 languages. Our findings shed light on the relative importance of similarity between the target and pretraining languages along the…

Computation and Language · Computer Science 2019-04-05 Oliver Adams , Matthew Wiesner , Shinji Watanabe , David Yarowsky

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…

Computation and Language · Computer Science 2026-03-09 Yuchen Zhang , Haralambos Mouratidis , Ravi Shekhar

Speech perception involves storing and integrating sequentially presented items. Recent work in cognitive neuroscience has identified temporal and contextual characteristics in humans' neural encoding of speech that may facilitate this…

Computation and Language · Computer Science 2024-05-15 Oli Danyi Liu , Hao Tang , Naomi Feldman , Sharon Goldwater

In machine learning applications, gradual data ingress is common, especially in audio processing where incremental learning is vital for real-time analytics. Few-shot class-incremental learning addresses challenges arising from limited…

Sound · Computer Science 2024-08-08 Riyansha Singh , Parinita Nema , Vinod K Kurmi

Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…

Computation and Language · Computer Science 2021-09-09 Ruiqi Zhong , Kristy Lee , Zheng Zhang , Dan Klein

The state of the art on many NLP tasks is currently achieved by large pre-trained language models, which require a considerable amount of computation. We explore a setting where many different predictions are made on a single piece of text.…

Computation and Language · Computer Science 2020-04-30 Jingfei Du , Myle Ott , Haoran Li , Xing Zhou , Veselin Stoyanov

Despite being trained on massive and diverse datasets, speech self-supervised encoders are generally used for downstream purposes as mere frozen feature extractors or model initializers before fine-tuning. The former severely limits the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-02 Salah Zaiem , Titouan Parcollet , Slim Essid

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…

Computation and Language · Computer Science 2020-02-24 Herman Kamper , Yevgen Matusevych , Sharon Goldwater

Multimodal large language models have fueled progress in image captioning. These models, fine-tuned on vast image datasets, exhibit a deep understanding of semantic concepts. In this work, we show that this ability can be re-purposed for…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-10 Hugo Malard , Michel Olvera , Stéphane Lathuiliere , Slim Essid

We learn audio representations by solving a novel self-supervised learning task, which consists of predicting the phase of the short-time Fourier transform from its magnitude. A convolutional encoder is used to map the magnitude spectrum of…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-29 Félix de Chaumont Quitry , Marco Tagliasacchi , Dominik Roblek

In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test sets from the same dataset. Such methods have two…

Sound · Computer Science 2024-06-11 Yiming Zhang , Xuenan Xu , Ruoyi Du , Haohe Liu , Yuan Dong , Zheng-Hua Tan , Wenwu Wang , Zhanyu Ma

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…

Sound · Computer Science 2024-02-09 Sungho Jeon , Ching-Feng Yeh , Hakan Inan , Wei-Ning Hsu , Rashi Rungta , Yashar Mehdad , Daniel Bikel

Automatic phonemic transcription tools are useful for low-resource language documentation. However, due to the lack of training sets, only a tiny fraction of languages have phonemic transcription tools. Fortunately, multilingual acoustic…

Computation and Language · Computer Science 2020-02-28 Xinjian Li , Siddharth Dalmia , David R. Mortensen , Juncheng Li , Alan W Black , Florian Metze

Audio-visual pre-trained models have gained substantial attention recently and demonstrated superior performance on various audio-visual tasks. This study investigates whether pre-trained audio-visual models demonstrate non-arbitrary…

Computation and Language · Computer Science 2024-11-13 Wei-Cheng Tseng , Yi-Jen Shih , David Harwath , Raymond Mooney

Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on…

We introduce a simple neural encoder architecture that can be trained using an unsupervised contrastive learning objective which gets its positive samples from data-augmented k-Nearest Neighbors search. We show that when built on top of…

Artificial Intelligence · Computer Science 2023-10-24 Robin Algayres , Adel Nabli , Benoit Sagot , Emmanuel Dupoux

Audio-visual zero-shot learning methods commonly build on features extracted from pre-trained models, e.g. video or audio classification models. However, existing benchmarks predate the popularization of large multi-modal models, such as…

Computer Vision and Pattern Recognition · Computer Science 2024-04-10 David Kurzendörfer , Otniel-Bogdan Mercea , A. Sophia Koepke , Zeynep Akata

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…

Supervised learning methods can solve the given problem in the presence of a large set of labeled data. However, the acquisition of a dataset covering all the target classes typically requires manual labeling which is expensive and…

Sound · Computer Science 2022-06-13 Duygu Dogan , Huang Xie , Toni Heittola , Tuomas Virtanen

Modeling various aspects that make a music piece unique is a challenging task, requiring the combination of multiple sources of information. Deep learning is commonly used to obtain representations using various sources of information, such…

Sound · Computer Science 2021-04-05 Andres Ferraro , Xavier Favory , Konstantinos Drossos , Yuntae Kim , Dmitry Bogdanov
‹ Prev 1 3 4 5 6 7 10 Next ›