28 citations · 30 across the 15 of their papers we have counts for
16 papers
OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models
Han Zhu, Lingxuan Ye, Wei Kang +7
We present OmniVoice, a massively multilingual zero-shot text-to-speech (TTS) model that scales to over 600 languages. At its core is a novel diffusion language model-style discret…
Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step High-Fidelity Audio Generation
Zengwei Yao, Wei Kang, Han Zhu +8
Existing dominant methods for audio generation include Generative Adversarial Networks (GANs) and diffusion-based methods like Flow Matching. GANs suffer from slow convergence duri…
ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching
Han Zhu, Wei Kang, Liyong Guo +11
Generating spoken dialogue is inherently more complex than monologue text-to-speech (TTS), as it demands both realistic turn-taking and the maintenance of distinct speaker timbres.…
ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
Han Zhu, Wei Kang, Zengwei Yao +6
Existing large-scale zero-shot text-to-speech (TTS) models deliver high speech quality but suffer from slow inference speeds due to massive parameters. To address this issue, this…
k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning
Yifan Yang, Jianheng Zhuo, Zengrui Jin +9
Self-supervised learning (SSL) has achieved great success in speech-related tasks. While Transformer and Conformer architectures have dominated SSL backbones, encoders like Zipform…
CR-CTC: Consistency regularization on CTC for improved speech recognition
Zengwei Yao, Wei Kang, Xiaoyu Yang +7
Connectionist Temporal Classification (CTC) is a widely used method for automatic speech recognition (ASR), renowned for its simplicity and computational efficiency. However, it of…
LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization
Zengrui Jin, Yifan Yang, Mohan Shi +10
The evolving speech processing landscape is increasingly focused on complex scenarios like meetings or cocktail parties with multiple simultaneous speakers and far-field conditions…
Zipformer: A faster and better encoder for automatic speech recognition
Zengwei Yao, Liyong Guo, Xiaoyu Yang +6
The Conformer has become the most popular encoder model for automatic speech recognition (ASR). It adds convolution modules to a transformer to learn both local and global dependen…
Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context
Wei Kang, Xiaoyu Yang, Zengwei Yao +5
In this paper, we introduce Libriheavy, a large-scale ASR corpus consisting of 50,000 hours of read English speech derived from LibriVox. To the best of our knowledge, Libriheavy i…
PromptASR for contextualized ASR with controllable style
Xiaoyu Yang, Wei Kang, Zengwei Yao +5
Prompts are crucial to large language models as they provide context information such as topic or logical relationships. Inspired by this, we propose PromptASR, a framework that in…
Blank-regularized CTC for Frame Skipping in Neural Transducer
Yifan Yang, Xiaoyu Yang, Liyong Guo +6
Neural Transducer and connectionist temporal classification (CTC) are popular end-to-end automatic speech recognition systems. Due to their frame-synchronous design, blank symbols…
Delay-penalized CTC implemented based on Finite State Transducer
Zengwei Yao, Wei Kang, Fangjun Kuang +5
Connectionist Temporal Classification (CTC) suffers from the latency problem when applied to streaming models. We argue that in CTC lattice, the alignments that can access more fut…
Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation
Liyong Guo, Xiaoyu Yang, Quandong Wang +9
Knowledge distillation(KD) is a common approach to improve model performance in automatic speech recognition (ASR), where a student model is trained to imitate the output behaviour…
Delay-penalized transducer for low-latency streaming ASR
Wei Kang, Zengwei Yao, Fangjun Kuang +5
In streaming automatic speech recognition (ASR), it is desirable to reduce latency as much as possible while having minimum impact on recognition accuracy. Although a few existing…
Fast and parallel decoding for transducer
Wei Kang, Liyong Guo, Fangjun Kuang +6
The transducer architecture is becoming increasingly popular in the field of speech recognition, because it is naturally streaming as well as high in accuracy. One of the drawbacks…
Pruned RNN-T for fast, memory-efficient ASR training
Fangjun Kuang, Liyong Guo, Wei Kang +4
The RNN-Transducer (RNN-T) framework for speech recognition has been growing in popularity, particularly for deployed real-time ASR systems, because it combines high accuracy with…