34 citations · 195 across the 59 of their papers we have counts for
18 papers · 1 filter
Connecting Speech Encoder and Large Language Model for ASR
Wenyi Yu, Changli Tang, Guangzhi Sun +6
The impressive capability and versatility of large language models (LLMs) have aroused increasing attention in automatic speech recognition (ASR), with several pioneering studies a…
Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis
Ziyue Jiang, Jinglin Liu, Yi Ren +10
Zero-shot text-to-speech (TTS) aims to synthesize voices with unseen speech prompts, which significantly reduces the data and computation requirements for voice cloning by skipping…
GenerTTS: Pronunciation Disentanglement for Timbre and Style Generalization in Cross-Lingual Text-to-Speech
Yahuan Cong, Haoyu Zhang, Haopeng Lin +5
Cross-lingual timbre and style generalizable text-to-speech (TTS) aims to synthesize speech with a specific reference timbre or style that is never trained in the target language.…
Improving Frame-level Classifier for Word Timings with Non-peaky CTC in End-to-End Automatic Speech Recognition
Xianzhao Chen, Yist Y. Lin, Kang Wang +2
End-to-end (E2E) systems have shown comparable performance to hybrid systems for automatic speech recognition (ASR). Word timings, as a by-product of ASR, are essential in many app…
Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias
Ziyue Jiang, Yi Ren, Zhenhui Ye +9
Scaling text-to-speech to a large and wild dataset has been proven to be highly effective in achieving timbre and speech style generalization, particularly in zero-shot TTS. Howeve…
Leveraging phone-level linguistic-acoustic similarity for utterance-level pronunciation scoring
Wei Liu, Kaiqi Fu, Xiaohai Tian +4
Recent studies on pronunciation scoring have explored the effect of introducing phone embeddings as reference pronunciation, but mostly in an implicit manner, i.e., addition or con…
An ASR-free Fluency Scoring Approach with Self-Supervised Learning
Wei Liu, Kaiqi Fu, Xiaohai Tian +4
A typical fluency scoring system generally relies on an automatic speech recognition (ASR) system to obtain time stamps in input speech for either the subsequent calculation of flu…
Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition
Yist Y. Lin, Tao Han, Haihua Xu +6
One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are mismatched. In this paper,…
Language Adaptive Cross-lingual Speech Representation Learning with Sparse Sharing Sub-networks
Yizhou Lu, Mingkun Huang, Xinghua Qu +2
Unsupervised cross-lingual speech representation learning (XLSR) has recently shown promising results in speech recognition by leveraging vast amounts of unlabeled data across mult…
Improving Non-native Word-level Pronunciation Scoring with Phone-level Mixup Data Augmentation and Multi-source Information
Kaiqi Fu, Shaojun Gao, Kai Wang +3
Deep learning-based pronunciation scoring models highly rely on the availability of the annotated non-native data, which is costly and has scalability issues. To deal with the data…
S3T: Self-Supervised Pre-training with Swin Transformer for Music Classification
Hang Zhao, Chen Zhang, Belei Zhu +2
In this paper, we propose S3T, a self-supervised pre-training method with Swin Transformer for music classification, aiming to learn meaningful music representations from massive e…
Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASR
Yufei Liu, Rao Ma, Haihua Xu +3
An end-to-end (E2E) ASR model implicitly learns a prior Internal Language Model (ILM) from the training transcripts. To fuse an external LM using Bayes posterior theory, the log li…
Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech
Pengfei Wu, Junjie Pan, Chenchang Xu +4
In expressive speech synthesis, there are high requirements for emotion interpretation. However, it is time-consuming to acquire emotional audio corpus for arbitrary speakers due t…
Improving Pseudo-label Training For End-to-end Speech Recognition Using Gradient Mask
Shaoshi Ling, Chen Shen, Meng Cai +1
In the recent trend of semi-supervised speech recognition, both self-supervised representation learning and pseudo-labeling have shown promising results. In this paper, we propose…
HMM-Free Encoder Pre-Training for Streaming RNN Transducer
Lu Huang, Jingyu Sun, Yufeng Tang +4
This work describes an encoder pre-training procedure using frame-wise label to improve the training of streaming recurrent neural network transducer (RNN-T) model. Streaming RNN-T…
Improving RNN transducer with normalized jointer network
Mingkun Huang, Jun Zhang, Meng Cai +5
Recurrent neural transducer (RNN-T) is a promising end-to-end (E2E) model in automatic speech recognition (ASR). It has shown superior performance compared to traditional hybrid AS…
Dynamic latency speech recognition with asynchronous revision
Mingkun Huang, Meng Cai, Jun Zhang +4
In this work we propose an inference technique, asynchronous revision, to unify streaming and non-streaming speech recognition models. Specifically, we achieve dynamic latency with…
ByteSing: A Chinese Singing Voice Synthesis System Using Duration Allocated Encoder-Decoder Acoustic Models and WaveRNN Vocoders
Yu Gu, Xiang Yin, Yonghui Rao +6
This paper presents ByteSing, a Chinese singing voice synthesis (SVS) system based on duration allocated Tacotron-like acoustic models and WaveRNN neural vocoders. Different from t…