Related papers: MOSNet: Deep Learning based Objective Assessment f…
Modern speech synthesis systems have improved significantly, with synthetic speech being indistinguishable from real speech. However, efficient and holistic evaluation of synthetic speech still remains a significant challenge. Human…
We present the UTokyo-SaruLab mean opinion score (MOS) prediction system submitted to VoiceMOS Challenge 2022. The challenge is to predict the MOS values of speech samples collected from previous Blizzard Challenges and Voice Conversion…
Large language models encode knowledge in various domains and demonstrate the ability to understand visualizations. They may also capture visualization design knowledge and potentially help reduce the cost of formative studies. However, it…
Speech Emotion Recognition (SER) presents a significant yet persistent challenge in human-computer interaction. While deep learning has advanced spoken language processing, achieving high performance on limited datasets remains a critical…
This paper introduces BWSNet, a model that can be trained from raw human judgements obtained through a Best-Worst scaling (BWS) experiment. It maps sound samples into an embedded space that represents the perception of a studied attribute.…
The Transformer architecture has demonstrated a superior ability compared to recurrent neural networks in many different natural language processing applications. Therefore, our study applies a modified Transformer in a speech enhancement…
One-shot voice conversion (VC), which performs conversion across arbitrary speakers with only a single target-speaker utterance for reference, can be effectively achieved by speech representation disentanglement. Existing work generally…
Here we present a novel approach to conditioning the SampleRNN generative model for voice conversion (VC). Conventional methods for VC modify the perceived speaker identity by converting between source and target acoustic features. Our…
PESQ and POLQA , are standards are standards for automated assessment of voice quality of speech as experienced by human beings. The predictions of those objective measures should come as close as possible to subjective quality scores as…
The mouse is one of the most studied animal models in the field of systems neuroscience. Understanding the generalized patterns and decoding the neural representations that are evoked by the diverse range of natural scene stimuli in the…
This paper investigates the performance of Deep Learning for speech emotion classification when the speech is compounded with noise. It reports on the classification accuracy and concludes with the future directions for achieving greater…
Objective estimators of multimedia quality are often judged by comparing estimates with subjective "truth data," most often via Pearson correlation coefficient (PCC) or mean-squared error (MSE). But subjective test results contain noise, so…
Vocal education in the music field is difficult to quantify due to the individual differences in singers' voices and the different quantitative criteria of singing techniques. Deep learning has great potential to be applied in music…
One-shot voice conversion aims to change the timbre of any source speech to match that of the unseen target speaker with only one speech sample. Existing methods face difficulties in satisfactory speech representation disentanglement and…
We propose MambaRate, which predicts Mean Opinion Scores (MOS) with limited bias regarding the sampling rate of the waveform under evaluation. It is designed for Track 3 of the AudioMOS Challenge 2025, which focuses on predicting MOS for…
Speaker recognition systems are widely used in various applications to identify a person by their voice; however, the high degree of variability in speech signals makes this a challenging task. Dealing with emotional variations is very…
So far, many of the deep learning approaches for voice conversion produce good quality speech by using a large amount of training data. This paper presents a Deep Bidirectional Long Short-Term Memory (DBLSTM) based voice conversion…
In this paper, we propose an improved LPCNet vocoder using a linear prediction (LP)-structured mixture density network (MDN). The recently proposed LPCNet vocoder has successfully achieved high-quality and lightweight speech synthesis…
Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. Nonetheless, without sufficient data, seq2seq VC models can suffer from unstable training and mispronunciation problems in…
Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. This prevents the feasibility of deployment on different input image resolutions for a specific model. To…