Related papers: Enhanced Voice Post Processing Using Voice Decoder…
Music information retrieval is currently an active research area that addresses the extraction of musically important information from audio signals, and the applications of such information. The extracted information can be used for search…
In this paper, we explore the encoding/pooling layer and loss function in the end-to-end speaker and language recognition system. First, a unified and interpretable end-to-end system for both speaker and language recognition is developed.…
Auxiliary function is a helpful component to improve language model's code generation ability. However, a systematic exploration of how they affect has yet to be done. In this work, we comprehensively evaluate the ability to utilize…
The goal of voice anonymization is to modify an audio such that the true identity of its speaker is hidden. Research on this task is typically limited to the same English read speech datasets, thus the efficacy of current methods for other…
Video captioning is an advanced multi-modal task which aims to describe a video clip using a natural language sentence. The encoder-decoder framework is the most popular paradigm for this task in recent years. However, there exist some…
The creation of artificial polyglot voices remains a challenging task, despite considerable progress in recent years. This paper investigates self-supervised learning for voice conversion to create native-sounding polyglot voices. We…
Applying changes to an input speech signal to change the perceived speaker of speech to a target while maintaining the content of the input is a challenging but interesting task known as Voice conversion (VC). Over the last few years, this…
Consumer-grade music recordings such as those captured by mobile devices typically contain distortions in the form of background noise, reverb, and microphone-induced EQ. This paper presents a deep learning approach to enhance low-quality…
The increasing use of cloud-based speech assistants has heightened the need for effective speech anonymization, which aims to obscure a speaker's identity while retaining critical information for subsequent tasks. One approach to achieving…
Deep learning-based works for singing voice separation have performed exceptionally well in the recent past. However, most of these works do not focus on allowing users to interact with the model to improve performance. This can be crucial…
This Ph.D. thesis focuses on developing a system for high-quality speech synthesis and voice conversion. Vocoder-based speech analysis, manipulation, and synthesis plays a crucial role in various kinds of statistical parametric speech…
Recent studies have explored the use of deep generative models of speech spectra based of variational autoencoders (VAEs), combined with unsupervised noise models, to perform speech enhancement. These studies developed iterative algorithms…
A command-following robot that serves people in everyday life must continually improve itself in deployment domains with minimal help from its end users, instead of engineers. Previous methods are either difficult to continuously improve…
The latest video coding standard, called versatile video coding (VVC), includes several novel and refined coding tools at different levels of the coding chain. These tools bring significant coding gains with respect to the previous…
This study compares the performances of different algorithms for coding speech at low bit rates. In addition to widely deployed traditional vocoders, a selection of recently developed generative-model-based coders at different bit rates are…
In mobile speech communication applications, wind noise can lead to a severe reduction of speech quality and intelligibility. Since the performance of speech enhancement algorithms using acoustic microphones tends to substantially degrade…
Decoder-only discrete-token language models have recently achieved significant success in automatic speech recognition. However, systematic analyses of how different modalities impact performance in specific scenarios remain limited. In…
The quality of audio recordings in outdoor environments is often degraded by the presence of wind. Mitigating the impact of wind noise on the perceptual quality of single-channel speech remains a significant challenge due to its…
Many existing works on voice conversion (VC) tasks use automatic speech recognition (ASR) models for ensuring linguistic consistency between source and converted samples. However, for the low-data resource domains, training a high-quality…
Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…