Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Ni, Chongjia"'
Autor:
An, Keyu, Chen, Qian, Deng, Chong, Du, Zhihao, Gao, Changfeng, Gao, Zhifu, Gu, Yue, He, Ting, Hu, Hangrui, Hu, Kai, Ji, Shengpeng, Li, Yabin, Li, Zerui, Lu, Heng, Luo, Haoneng, Lv, Xiang, Ma, Bin, Ma, Ziyang, Ni, Chongjia, Song, Changhe, Shi, Jiaqi, Shi, Xian, Wang, Hao, Wang, Wen, Wang, Yuxuan, Xiao, Zhangyu, Yan, Zhijie, Yang, Yexin, Zhang, Bin, Zhang, Qinglin, Zhang, Shiliang, Zhao, Nan, Zheng, Siqi
This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions between humans and large language models (LLMs). At its core are two innovative models: SenseVoice, which handles multilingual speech recognition, emoti
Externí odkaz:
http://arxiv.org/abs/2407.04051
Autor:
Zhou, Kun, Zhao, Shengkui, Ma, Yukun, Zhang, Chong, Wang, Hao, Ng, Dianwen, Ni, Chongjia, Hieu, Nguyen Trung, Yip, Jia Qi, Ma, Bin
Recent language model-based text-to-speech (TTS) frameworks demonstrate scalability and in-context learning capabilities. However, they suffer from robustness issues due to the accumulation of errors in speech unit predictions during autoregressive l
Externí odkaz:
http://arxiv.org/abs/2406.02009
Autor:
Zhao, Shengkui, Ma, Yukun, Ni, Chongjia, Zhang, Chong, Wang, Hao, Nguyen, Trung Hieu, Zhou, Kun, Yip, Jiaqi, Ng, Dianwen, Ma, Bin
Our previously proposed MossFormer has achieved promising performance in monaural speech separation. However, it predominantly adopts a self-attention-based MossFormer module, which tends to emphasize longer-range, coarser-scale dependencies, with a
Externí odkaz:
http://arxiv.org/abs/2312.11825
Autor:
Yip, Jia Qi, Zhao, Shengkui, Ma, Yukun, Ni, Chongjia, Zhang, Chong, Wang, Hao, Nguyen, Trung Hieu, Zhou, Kun, Ng, Dianwen, Chng, Eng Siong, Ma, Bin
Dual-path is a popular architecture for speech separation models (e.g. Sepformer) which splits long sequences into overlapping chunks for its intra- and inter-blocks that separately model intra-chunk local features and inter-chunk global relationship
Externí odkaz:
http://arxiv.org/abs/2309.12608
Autor:
Ng, Dianwen, Zhang, Chong, Zhang, Ruixi, Ma, Yukun, Ritter-Gutierrez, Fabian, Nguyen, Trung Hieu, Ni, Chongjia, Zhao, Shengkui, Chng, Eng Siong, Ma, Bin
Large self-supervised pre-trained speech models require computationally expensive fine-tuning for downstream tasks. Soft prompt tuning offers a simple parameter-efficient alternative by utilizing minimal soft prompt guidance, enhancing portability wh
Externí odkaz:
http://arxiv.org/abs/2309.09413
Autor:
Yip, Jia Qi, Truong, Tuan, Ng, Dianwen, Zhang, Chong, Ma, Yukun, Nguyen, Trung Hieu, Ni, Chongjia, Zhao, Shengkui, Chng, Eng Siong, Ma, Bin
In this paper, we propose ACA-Net, a lightweight, global context-aware speaker embedding extractor for Speaker Verification (SV) that improves upon existing work by using Asymmetric Cross Attention (ACA) to replace temporal pooling. ACA is able to di
Externí odkaz:
http://arxiv.org/abs/2305.12121
Autor:
Ng, Dianwen, Zhang, Ruixi, Yip, Jia Qi, Zhang, Chong, Ma, Yukun, Nguyen, Trung Hieu, Ni, Chongjia, Chng, Eng Siong, Ma, Bin
Most of the existing neural-based models for keyword spotting (KWS) in smart devices require thousands of training samples to learn a decent audio representation. However, with the rising demand for smart devices to become more personalized, KWS mode
Externí odkaz:
http://arxiv.org/abs/2305.01170
Autor:
Ng, Dianwen, Zhang, Ruixi, Yip, Jia Qi, Yang, Zhao, Ni, Jinjie, Zhang, Chong, Ma, Yukun, Ni, Chongjia, Chng, Eng Siong, Ma, Bin
Existing self-supervised pre-trained speech models have offered an effective way to leverage massive unannotated corpora to build good automatic speech recognition (ASR). However, many current models are trained on a clean corpus from a single source
Externí odkaz:
http://arxiv.org/abs/2302.14597
This paper provides an overall introduction of our Automatic Speech Recognition (ASR) systems for Southeast Asian languages. As not much existing work has been carried out on such regional languages, a few difficulties should be addressed before buil
Externí odkaz:
http://arxiv.org/abs/2210.03580
Autor:
Ng, Dianwen, Yip, Jia Qi, Surana, Tanmay, Yang, Zhao, Zhang, Chong, Ma, Yukun, Ni, Chongjia, Chng, Eng Siong, Ma, Bin
Noise robustness in keyword spotting remains a challenge as many models fail to overcome the heavy influence of noises, causing the deterioration of the quality of feature embeddings. We proposed a contrastive regularization method called Inter-Intra
Externí odkaz:
http://arxiv.org/abs/2209.06360