Related papers: PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spo…

We propose a novel language-universal approach to end-to-end automatic spoken keyword recognition (SKR) leveraging upon (i) a self-supervised pre-trained model, and (ii) a set of universal speech attributes (manner and place of…

Language models built using semi-supervised machine learning on large corpora of natural language have very quickly enveloped the fields of natural language generation and understanding. In this paper we apply a zero-shot approach…

Deep learning-based pronunciation scoring models highly rely on the availability of the annotated non-native data, which is costly and has scalability issues. To deal with the data scarcity problem, data augmentation is commonly used for…

Existing zero-shot cross-lingual NER approaches require substantial prior knowledge of the target language, which is impractical for low-resource languages. In this paper, we propose a novel approach to NER using phonemic representation…

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…

This work investigates two strategies for zero-shot non-intrusive speech assessment leveraging large language models. First, we explore the audio analysis capabilities of GPT-4o. Second, we propose GPT-Whisper, which uses Whisper as an…

Recent years have witnessed significant improvement in ASR systems to recognize spoken utterances. However, it is still a challenging task for noisy and out-of-domain data, where substitution and deletion errors are prevalent in the…

Despite rapid advancement in recent years, current speech enhancement models often produce speech that differs in perceptual quality from real clean speech. We propose a learning objective that formalizes differences in perceptual quality,…

End-to-end speech synthesis models directly convert the input characters into an audio representation (e.g., spectrograms). Despite their impressive performance, such models have difficulty disambiguating the pronunciations of identically…

In this work, we revisit the prior mask guidance proposed in ``Prior Guided Feature Enrichment Network for Few-Shot Segmentation''. The prior mask serves as an indicator that highlights the region of interests of unseen categories, and it…

Many applications involve detecting and localizing specific sound events within long, untrimmed documents, including keyword spotting, medical observation, and bioacoustic monitoring for conservation. Deep learning techniques often set the…

Zero-shot audio captioning aims at automatically generating descriptive textual captions for audio content without prior training for this task. Different from speech recognition which translates audio content that contains spoken language…

How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data? Pre-trained language models (PLMs) have been effective for a wide range of NLP tasks. However, existing approaches…

Few-shot keyword spotting aims to detect previously unseen keywords with very limited labeled samples. A pre-training and adaptation paradigm is typically adopted for this task. While effective in clean conditions, most existing approaches…

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…

Many applications of speech technology require more and more audio data. Automatic assessment of the quality of the collected recordings is important to ensure they meet the requirements of the related applications. However, effective and…

A personalized KeyWord Spotting (KWS) pipeline typically requires the training of a Deep Learning model on a large set of user-defined speech utterances, preventing fast customization directly applied on-device. To fill this gap, this paper…

State-of-the-art audio classification often employs a zero-shot approach, which involves comparing audio embeddings with embeddings from text describing the respective audio class. These embeddings are usually generated by neural networks…

Keyword spotting is an important research field because it plays a key role in device wake-up and user interaction on smart devices. However, it is challenging to minimize errors while operating efficiently in devices with limited resources…

Automatic pronunciation assessment is typically performed by acoustic models trained on audio-score pairs. Although effective, these systems provide only numerical scores, without the information needed to help learners understand their…