Related papers: Automating Sound Change Prediction for Phylogeneti…
Automatic speech recognition systems are part of people's daily lives, embedded in personal assistants and mobile phones, helping as a facilitator for human-machine interaction while allowing access to information in a practically intuitive…
Recent studies on pronunciation scoring have explored the effect of introducing phone embeddings as reference pronunciation, but mostly in an implicit manner, i.e., addition or concatenation of reference phone embedding and actual…
Automatic speech recognition is a difficult problem in pattern recognition because several sources of variability exist in the speech input like the channel variations, the input might be clean or noisy, the speakers may have different…
We focus on using the predictive uncertainty signal calculated by Bayesian neural networks to guide learning in the self-same task the model is being trained on. Not opting for costly Monte Carlo sampling of weights, we propagate the…
For articulatory-to-acoustic mapping, typically only limited parallel training data is available, making it impossible to apply fully end-to-end solutions like Tacotron2. In this paper, we experimented with transfer learning and adaptation…
We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their…
Neural language models are usually trained to match the distributional properties of a large-scale corpus by minimizing the log loss. While straightforward to optimize, this approach forces the model to reproduce all variations in the…
In this article, we present an approach for non native automatic speech recognition (ASR). We propose two methods to adapt existing ASR systems to the non-native accents. The first method is based on the modification of acoustic models…
The range of potential applications of acoustic analysis is wide. Classification of sounds, in particular, is a typical machine learning task that received a lot of attention in recent years. The most common approaches to sound…
This paper presents a novel approach for detecting mispronunciations by analyzing deviations between a user's original speech and their voice-cloned counterpart with corrected pronunciation. We hypothesize that regions with maximal acoustic…
Accent plays a crucial role in speaker identity and inclusivity in speech technologies. Existing accented text-to-speech (TTS) systems either require large-scale accented datasets or lack fine-grained phoneme-level controllability. We…
Although end-to-end text-to-speech (TTS) models can generate natural speech, challenges still remain when it comes to estimating sentence-level phonetic and prosodic information from raw text in Japanese TTS systems. In this paper, we…
Our native language influences the way we perceive speech sounds, affecting our ability to discriminate non-native sounds. We compare two ideas about the influence of the native language on speech perception: the Perceptual Assimilation…
Monitoring remote forests is a global challenge central to climate mitigation and biodiversity conservation, yet satellite observations are frequently limited by weather, dense canopies, and solar dependency. Here we show that passive…
Reconciling a gene tree with a species tree is an important task that reveals much about the evolution of genes, genomes, and species, as well as about the molecular function of genes. A wide array of computational tools have been devised…
Articulatory-to-acoustic (forward) mapping is a technique to predict speech using various articulatory acquisition techniques as input (e.g. ultrasound tongue imaging, MRI, lip video). The advantage of lip video is that it is easily…
Researches on sequential vocalization often require analysis of vocalizations in long continuous sounds. In such studies as developmental ones or studies across generations in which days or months of vocalizations must be analyzed, methods…
Discriminative training techniques define state-of-the-art performance for automatic speech recognition systems. However, they are inherently prone to overfitting, leading to poor generalization performance when using limited training data.…
In this paper I report on an investigation into the problem of assigning tones to pitch contours. The proposed model is intended to serve as a tool for phonologists working on instrumentally obtained pitch data from tone languages.…
Structural information of phylogenetic tree topologies plays an important role in phylogenetic inference. However, finding appropriate topological structures for specific phylogenetic inference tasks often requires significant design effort…