Audio

Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy
Because of predicting all the target tokens in parallel, the non-autoregressive models greatly improve the decoding efficiency of …
Cite arXiv IEEE
Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy
Improving Music Genre Classification from Multi-modal Properties of Music and Genre Correlations Perspective
Music genre classification has been widely studied in past few years for its various applications in music information retrieval. …
Cite Poster arXiv IEEE
Improving Music Genre Classification from Multi-modal Properties of Music and Genre Correlations Perspective
Learning Speech Representations with Flexible Hidden Feature Dimensions
Non-parallel many-to-many voice conversion is a kind of style transfer task in speech. Recently, AutoVC has been applied in this field …
PDF Cite IEEE
Learning Speech Representations with Flexible Hidden Feature Dimensions
QI-TTS: Questioning Intonation Control for Emotional Speech Synthesis
Recent expressive text to speech (TTS) models focus on synthesizing emotional speech, but some fine-grained styles such as intonation …
Cite arXiv IEEE
QI-TTS: Questioning Intonation Control for Emotional Speech Synthesis
VQ-CL: Learning Disentangled Speech Representations with Contrastive Learning and Vector Quantization
Voice Conversion(VC) refers to converting the voice char- acteristics of audio to another one as it is said by other people. Recently, …
PDF Cite IEEE
VQ-CL: Learning Disentangled Speech Representations with Contrastive Learning and Vector Quantization
Feature-Rich Audio Model Inversion for Data-Free Knowledge Distillation Towards General Sound Classification
Data-Free Knowledge Distillation (DFKD) has recently attracted growing attention in the academic community, especially with major …
Cite arXiv IEEE
Feature-Rich Audio Model Inversion for Data-Free Knowledge Distillation Towards General Sound Classification
Melody Generation from Lyrics with Local Interpretability
Melody generation aims to learn the distribution of real melodies to generate new melodies conditioned on lyrics, which has been a very …
Cite ACM
Melody Generation from Lyrics with Local Interpretability
SVLDL: Improved Speaker Age Estimation Using Selective Variance Label Distribution Learning
Estimating age from a single speech is a classic and challenging topic. Although Label Distribution Learning (LDL) can represent …
Cite arXiv IEEE
SVLDL: Improved Speaker Age Estimation Using Selective Variance Label Distribution Learning
Adapitch: Adaption Multi-Speaker Text-to-Speech Conditioned on Pitch Disentangling with Untranscribed Data
In this paper, we proposed Adapitch, a multi-speaker TTS method that makes adaptation of the supervised module with untranscribed data. …
Cite arXiv IEEE
Adapitch: Adaption Multi-Speaker Text-to-Speech Conditioned on Pitch Disentangling with Untranscribed Data
Improving Speech Representation Learning via Speech-level and Phoneme-level Masking Approach
Recovering the masked speech frames is widely applied in speech representation learning. However, most of these models use random …
Cite arXiv IEEE
Improving Speech Representation Learning via Speech-level and Phoneme-level Masking Approach