Related papers: PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spo…
Stance detection is an important component of understanding hidden influences in everyday life. Since there are thousands of potential topics to take a stance on, most with little to no training data, we focus on zero-shot stance detection:…
Speech enhancement has seen great improvement in recent years using end-to-end neural networks. However, most models are agnostic to the spoken phonetic content. Recently, several studies suggested phonetic-aware speech enhancement, mostly…
We propose UNIVERSE++, a universal speech enhancement method based on score-based diffusion and adversarial training. Specifically, we improve the existing UNIVERSE model that decouples clean speech feature extraction and diffusion. Our…
Slot filling is identifying contiguous spans of words in an utterance that correspond to certain parameters (i.e., slots) of a user request/query. Slot filling is one of the most important challenges in modern task-oriented dialog systems.…
Mispronunciation Detection and Diagnosis (MDD) is crucial for language learning and speech therapy. Unlike conventional methods that require scoring models or training phoneme-level models, we propose a novel training-free framework that…
We propose a self-supervised representation learning model for the task of unsupervised phoneme boundary detection. The model is a convolutional neural network that operates directly on the raw waveform. It is optimized to identify spectral…
This study tackles unsupervised subword modeling in the zero-resource scenario, learning frame-level speech representation that is phonetically discriminative and speaker-invariant, using only untranscribed speech for target languages.…
Audio-Language Models (ALMs) have recently achieved remarkable success in zero-shot audio recognition tasks, which match features of audio waveforms with class-specific text prompt features, inspired by advancements in Vision-Language…
User-defined keyword spotting (KWS) is crucial for personalized voice interaction, yet existing methods face several challenges: (1) insufficient discriminability among confusable words, (2) performance inconsistency across speakers with…
This paper presents a new approach for unsupervised Spoken Term Detection with spoken queries using multiple sets of acoustic patterns automatically discovered from the target corpus. The different pattern HMM configurations(number of…
Learning to recognize new keywords with just a few examples is essential for personalizing keyword spotting (KWS) models to a user's choice of keywords. However, modern KWS models are typically trained on large datasets and restricted to a…
In noisy conditions, knowing speech contents facilitates listeners to more effectively suppress background noise components and to retrieve pure speech signals. Previous studies have also confirmed the benefits of incorporating phonetic…
Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement.…
This paper describes our submission of the WMT 2020 Shared Task on Sentence Level Direct Assessment, Quality Estimation (QE). In this study, we empirically reveal the \textit{mismatching issue} when directly adopting BERTScore to QE.…
This article investigates a zero-shot approach to hypernymy prediction using large language models (LLMs). The study employs a method based on text probability calculation, applying it to various generated prompts. The experiments…
For decades, context-dependent phonemes have been the dominant sub-word unit for conventional acoustic modeling systems. This status quo has begun to be challenged recently by end-to-end models which seek to combine acoustic, pronunciation,…
In this paper, we study the performance of few-shot learning, specifically meta learning empowered few-shot relation networks, over supervised deep learning and conventional machine learning approaches in the problem of Sound Source…
This paper explores a simple method for improving the zero-shot learning abilities of language models. We show that instruction tuning -- finetuning language models on a collection of tasks described via instructions -- substantially…
In this study we developed an automated system that evaluates speech and language features from audio recordings of neuropsychological examinations of 92 subjects in the Framingham Heart Study. A total of 265 features were used in an…
Note-level automatic music transcription is one of the most representative music information retrieval (MIR) tasks and has been studied for various instruments to understand music. However, due to the lack of high-quality labeled data,…