Audio

Linguistic-Enhanced Transformer with CTC Embedding for Speech Recognition
The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement …
Cite arXiv IEEE
Linguistic-Enhanced Transformer with CTC Embedding for Speech Recognition
MetaSpeech: Speech Effects Switch Along with Environment for Metaverse
Metaverse expands the physical world to a new dimension, and the physical environment and Metaverse environment can be directly …
Cite arXiv IEEE
MetaSpeech: Speech Effects Switch Along with Environment for Metaverse
Semi-Supervised Learning Based on Reference Model for Low-resource TTS
Most previous neural text-to-speech (TTS) methods are mainly based on supervised learning methods, which means they depend on a large …
Cite arXiv IEEE
Semi-Supervised Learning Based on Reference Model for Low-resource TTS
Shallow Diffusion Motion Model for Talking Face Generation from Speech
Talking face generation is synthesizing a lip synchronized talking face video by inputting an arbitrary face image and audio clips. …
PDF Cite Springer
Shallow Diffusion Motion Model for Talking Face Generation from Speech
Boosting Star-GANs for Voice Conversion with Contrastive Discriminator
Nonparallel multi-domain voice conversion methods such as the StarGAN-VCs have been widely applied in many scenarios. However, the …
Cite arXiv Springer
Boosting Star-GANs for Voice Conversion with Contrastive Discriminator
Pre-Avatar: An Automatic Presentation Generation Framework Leveraging Talking Avatar
Since the beginning of the COVID-19 pandemic, remote conferencing and school-teaching have become important tools. The previous …
Cite arXiv IEEE
Pre-Avatar: An Automatic Presentation Generation Framework Leveraging Talking Avatar
Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion
One-shot voice conversion (VC) with only a single target-speaker speech for reference has become a new research direction. Existing …
PDF Cite arXiv ISCA DEMO
Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion
SpeechEQ: Speech Emotion Recognition based on Multi-scale Unified Datasets and Multitask Learning
Speech emotion recognition (SER) has many challenges, but one of the main challenges is that each framework does not have a unified …
PDF Cite arXiv ISCA
SpeechEQ: Speech Emotion Recognition based on Multi-scale Unified Datasets and Multitask Learning
Tiny-Sepformer: A Tiny Time-Domain Transformer Network For Speech Separation
Time-domain Transformer neural networks have proven their superiority in speech separation tasks. However, these models usually have a …
PDF Cite arXiv ISCA
Tiny-Sepformer: A Tiny Time-Domain Transformer Network For Speech Separation
Uncertainty Calibration for Deep Audio Classifiers
Although deep Neural Networks (DNNs) have achieved tremendous success in audio classification tasks, their uncertainty calibration are …
PDF Cite ISCA
Uncertainty Calibration for Deep Audio Classifiers