Related papers: Learnable Frontends that do not Learn: Quantifying…
Advanced auditory models are useful in designing signal-processing algorithms for hearing-loss compensation or speech enhancement. Such auditory models provide rich and detailed descriptions of the auditory pathway, and might allow for…
Bioacoustics, the study of animal sounds, offers a non-invasive method to monitor ecosystems. Extracting embeddings from audio-pretrained deep learning (DL) models without fine-tuning has become popular for obtaining bioacoustic features…
Currently, deep neural networks are the state of the art on problems such as speech recognition and computer vision. In this extended abstract, we show that shallow feed-forward networks can learn the complex functions previously learned by…
Training deep neural networks on well-understood dependencies in speech data can provide new insights into how they learn internal representations. This paper argues that acquisition of speech can be modeled as a dependency between random…
While deep learning has achieved phenomenal successes in many AI applications, its enormous model size and intensive computation requirements pose a formidable challenge to the deployment in resource-limited nodes. There has recently been…
Recent generative models have significantly advanced speech restoration tasks, yet their training objectives often misalign with human perceptual preferences, resulting in suboptimal quality. While post-training alignment has proven…
Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy…
Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on…
We investigate the potential of stochastic neural networks for learning effective waveform-based acoustic models. The waveform-based setting, inherent to fully end-to-end speech recognition systems, is motivated by several comparative…
Discrete diffusion models are a powerful class of generative models with strong performance across many domains. For efficiency, however, discrete diffusion typically parameterizes the generative (reverse) process with factorized…
In this work, we propose a multi-head relevance weighting framework to learn audio representations from raw waveforms. The audio waveform, split into windows of short duration, are processed with a 1-D convolutional layer of cosine…
Rapid progress in machine learning for natural language processing has the potential to transform debates about how humans learn language. However, the learning environments and biases of current artificial learners and humans diverge in…
In the first year of life, infants' speech perception becomes attuned to the sounds of their native language. Many accounts of this early phonetic learning exist, but computational models predicting the attunement patterns observed in…
Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…
For centuries researchers have used sound to monitor and study wildlife. Traditionally, conservationists have identified species by ear; however, it is now common to deploy audio recording technology to monitor animal and ecosystem sounds.…
Deep learning techniques have considerably improved speech processing in recent years. Speaker representations extracted by deep learning models are being used in a wide range of tasks such as speaker recognition and speech emotion…
Recently, deep neural networks such as RNN, CNN and Transformer have been applied in the task of sequential recommendation, which aims to capture the dynamic preference characteristics from logged user behavior data for accurate…
While end-to-end systems are becoming popular in auditory signal processing including automatic music tagging, models using raw audio as input needs a large amount of data and computational resources without domain knowledge. Inspired by…
Continuously adapting pre-trained models to local data on resource constrained edge devices is the $\emph{last mile}$ for model deployment. However, as models increase in size and depth, backpropagation requires a large amount of memory,…
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…