Search Results for author:
Found 13 papers, 3 papers with code
StreamVoice+: Evolving into End-to-end Streaming Zero-shot Voice Conversion
StreamVoice+ integrates a semantic encoder and a connector with the original StreamVoice framework, now trained using a non-streaming ASR.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
SCDNet: Self-supervised Learning Feature-based Speaker Change Detection
Furthermore, a contrastive learning method is proposed to mitigate the overfitting tendencies in the training of both the fine-tuning-based method and SCDNet.
StreamVoice: Streamable Context-Aware Language Modeling for Real-time Zero-Shot Voice Conversion
Specifically, to enable streaming capability, StreamVoice employs a fully causal context-aware LM with a temporal-independent acoustic predictor, while alternately processing semantic and acoustic features at each time step of autoregression which eliminates the dependence on complete source speech.
MSM-VC: High-fidelity Source Style Transfer for Non-Parallel Voice Conversion by Multi-scale Style Modeling
In addition to conveying the linguistic content from source speech to converted speech, maintaining the speaking style of source speech also plays an important role in the voice conversion (VC) task, which is essential in many scenarios with highly expressive source speech, such as dubbing and data augmentation.
Delivering Speaking Style in Low-resource Voice Conversion with Multi-factor Constraints
Conveying the linguistic content and maintaining the source speech's speaking style, such as intonation and emotion, is essential in voice conversion (VC).
Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios
Moreover, the explicit prosody features used in the prosody predicting module can increase the diversity of synthetic speech by adjusting the value of prosody features.
AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person
In this paper, we present an automatic method to generate synchronized speech and talking-head videos on the basis of text and a single face image of an arbitrary person as input.
Show and Speak: Directly Synthesize Spoken Description of Images
This paper proposes a new model, referred to as the show and speak (SAS) model that, for the first time, is able to directly synthesize spoken descriptions of images, bypassing the need for any text or phonemes.
S2IGAN: Speech-to-Image Generation via Adversarial Learning
An estimated half of the world's languages do not have a written form, making it impossible for these languages to benefit from any existing text-based technologies.
Domain segmentation and adjustment for generalized zero-shot learning
In the generalized zero-shot learning, synthesizing unseen data with generative models has been the most popular method to address the imbalance of training data between seen and unseen classes.
Competing Ratio Loss for Discriminative Multi-class Image Classification
However, during the training of the deep convolutional neural network, the value of NLLR is not always positive or negative, which severely affects the convergence of NLLR.
Competing Ratio Loss for Discriminative Multi-class Image Classification
A lot of studies of image classification based on deep convolutional neural network focus on the network structure to improve the image classification performance.
Visual Space Optimization for Zero-shot Learning
The other is to optimize the visual feature structure in an intermediate embedding space, and in this method we successfully devise a multilayer perceptron framework based algorithm that is able to learn the common intermediate embedding space and meanwhile to make the visual data structure more distinctive.
