相关论文: A Diffeomorphic Flow-based Variational Framework f…

We propose a deep beamforming framework for enhancing target speaker(s) in multi-speaker environments. A deep neural network (DNN) is trained to estimate beamforming weights directly from noisy multichannel inputs while satisfying linear…

Generative flow networks (GFNs) are a class of models for sequential sampling of composite objects, which approximate a target distribution that is defined in terms of an energy function or a reward. GFNs are typically trained using a flow…

Japan's kairanban culture and idobata conversations have long functioned as traditional communication practices that foster nuanced dialogue among community members and contribute to the formation of social balance. Inspired by these…

In this paper, we propose a novel voice conversion strategy to resolve the mismatch between the training and conversion scenarios when parallel speech corpus is unavailable for training. Based on auto-encoder and disentanglement frameworks,…

We propose a novel neural waveform compression method to catalyze emerging speech semantic communications. By introducing nonlinear transform and variational modeling, we effectively capture the dependencies within speech frames and…

We propose a Text-to-Speech method to create an unseen expressive style using one utterance of expressive speech of around one second. Specifically, we enhance the disentanglement capabilities of a state-of-the-art sequence-to-sequence…

This paper focuses on using voice conversion (VC) to improve the speech intelligibility of surgical patients who have had parts of their articulators removed. Due to the difficulty of data collection, VC without parallel data is highly…

We introduce VocAlign, a novel source-free domain adaptation framework specifically designed for VLMs in open-vocabulary semantic segmentation. Our method adopts a student-teacher paradigm enhanced with a vocabulary alignment strategy,…

Despite the great promise of Transformers in many sequence modeling tasks (e.g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation. Previous work…

Aligning Large Language Models (LLMs) with the diverse spectrum of human values remains a central challenge: preference-based methods often fail to capture deeper motivational principles. Value-based approaches offer a more principled path,…

In this work, we address the problem of finegrained traceback of emotional and manipulation characteristics from synthetically manipulated speech. We hypothesize that combining semantic-prosodic cues captured by Speech Foundation Models…

We propose an adversarial learning approach for generating multi-turn dialogue responses. Our proposed framework, hredGAN, is based on conditional generative adversarial networks (GANs). The GAN's generator is a modified hierarchical…

We propose Mask CycleGAN, a novel architecture for unpaired image domain translation built based on CycleGAN, with an aim to address two issues: 1) unimodality in image translation and 2) lack of interpretability of latent variables. Our…

In this paper, we present a latent variable (LV) framework to identify all the speakers and their keywords given a multi-speaker mixture signal. We introduce two separate LVs to denote active speakers and the keywords uttered. The…

The Emotional Voice Conversion (EVC) aims to convert the discrete emotional state from the source emotion to the target for a given speech utterance while preserving linguistic content. In this paper, we propose regularizing emotion…

Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and…

Sentiment analysis of user-generated reviews or comments on products and services in social networks can help enterprises to analyze the feedback from customers and take corresponding actions for improvement. To mitigate large-scale…

Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech…

Generative Flow Networks (GFlowNets) are amortized inference models designed to sample from unnormalized distributions over composable objects, with applications in generative modeling for tasks in fields such as causal discovery, NLP, and…

Emotional voice conversion (EVC) involves modifying various acoustic characteristics, such as pitch and spectral envelope, to match a desired emotional state while preserving the speaker's identity. Existing EVC methods often rely on text…