Related papers: Blow: a single-scale hyperconditioned flow for non…
Traditional structured prediction models try to learn the conditional likelihood, i.e., p(y|x), to capture the relationship between the structured output y and the input features x. For many models, computing the likelihood is intractable.…
Engineering complex systems (aircraft, buildings, vehicles) requires coordinating geometric and performance couplings across subsystems. As generative models proliferate for specialized domains, a key research gap is how to coordinate…
Speech enhancement plays an essential role in improving the quality of speech signals in noisy environments. This paper investigates the efficacy of integrating Bidirectional Gated Recurrent Units (BGRU) and Transformer models for speech…
Voice Conversion (VC) is a technique that aims to transform the non-linguistic information of a source utterance to change the perceived identity of the speaker. While there is a rich literature on VC, most proposed methods are trained and…
Flow Matching has emerged as a powerful framework for learning continuous transformations between distributions, enabling high-fidelity generative modeling. This work introduces Symmetrical Flow Matching (SymmFlow), a new formulation that…
In this work we introduce a semi-supervised approach to the voice conversion problem, in which speech from a source speaker is converted into speech of a target speaker. The proposed method makes use of both parallel and non-parallel…
Voice conversion is a task to convert a non-linguistic feature of a given utterance. Since naturalness of speech strongly depends on its pitch pattern, in some applications, it would be desirable to keep the original rise/fall pitch pattern…
The BLOOM model is a large publicly available multilingual language model, but its pretraining was limited to 46 languages. To extend the benefits of BLOOM to other languages without incurring prohibitively large costs, it is desirable to…
Large Language Models (LLMs) have resulted in a surging demand for planet-scale serving systems, where tens of thousands of GPUs continuously serve hundreds of millions of users. Consequently, throughput has emerged as a key metric that…
Diffusion probabilistic models have shown impressive performance for speech enhancement, but they typically require 25 to 60 function evaluations in the inference phase, resulting in heavy computational complexity. Recently, a fine-tuning…
Natural language understanding and dialogue policy learning are both essential in conversational systems that predict the next system actions in response to a current user utterance. Conventional approaches aggregate separate models of…
Flow-based generative models have highly desirable properties like exact log-likelihood evaluation and exact latent-variable inference, however they are still in their infancy and have not received as much attention as alternative…
One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the…
Zero-shot spoken language understanding (SLU) enables systems to comprehend user utterances in new domains without prior exposure to training data. Recent studies often rely on large language models (LLMs), leading to excessive footprints…
Disorders of voice production have severe effects on the quality of life of the affected individuals. A simulation approach is used to investigate the cause-effect chain in voice production showing typical characteristics of voice such as…
It is relatively easy to mine a large parallel corpus for any machine learning task, such as speech-to-text or speech-to-speech translation. Although these mined corpora are large in volume, their quality is questionable. This work shows…
We consider the problem of separating a particular sound source from a single-channel mixture, based on only a short sample of the target source. Using SoundFilter, a wave-to-wave neural network architecture, we can train a model without…
This paper introduces a cross-lingual dubbing system that translates speech from one language to another while preserving key characteristics such as duration, speaker identity, and speaking speed. Despite the strong translation quality of…
Adapting large language models to other languages typically employs supervised fine-tuning (SFT) as a standard approach. However, it often suffers from an overemphasis on English performance, a phenomenon that is especially pronounced in…
Thanks to the growing availability of spoofing databases and rapid advances in using them, systems for detecting voice spoofing attacks are becoming more and more capable, and error rates close to zero are being reached for the ASVspoof2015…