Research on speech recognition, synthesis, and spoken interaction. Follow results on audio quality, language coverage, and robustness.
27 papers · Latest edition October 3, 2026
Three of the latest briefs in this collection. Read the evidence and the original papers alongside them.
A new CTC training strategy makes large-vocabulary LLM speech recognition far more memory-efficient while retaining competitive accuracy and fast streaming inference.
The study argues that voice-similarity systems should be judged by whether their embedding geometry matches human perception, not merely by verification accuracy.
Tacit-TTS makes zero-shot voice cloning over ten times faster while preserving the ability to clone voices from speech without transcripts, including multilingual and non-lexical references.
Newest editions first.
Yifan Yang, Xiaoyu Yang, Zengrui Jin, Xian Shi, Yuxuan Wang, Yu Xi, Ziyang Ma, Qi Chen, Ruiyang Xu, Hui Wang, Dongchao Yang, Jin Xu, Xie Chen
A new CTC training strategy makes large-vocabulary LLM speech recognition far more memory-efficient while retaining competitive accuracy and fast streaming inference.
Szu-Chi Chen, Jia-Kai Dong, Yi-Cheng Lin, Sung-Feng Huang, Hung-yi Lee
The study argues that voice-similarity systems should be judged by whether their embedding geometry matches human perception, not merely by verification accuracy.
Jian Chen, You Zhang, Mark Vinton
Tacit-TTS makes zero-shot voice cloning over ten times faster while preserving the ability to clone voices from speech without transcripts, including multilingual and non-lexical references.
Kunat Pipatanakul, Potsawee Manakul, Warit Sirichotedumrong, Sittipong Sripaisarnmongkol, Pakorn Nathong, Phatrasek Jirabovonvisut
A large voice-cloning model becomes a synthetic data generator for training a compact, reference-free Thai TTS system that runs on-device.
Bin Lin, Bo Zhao, Boyang Zhang, Boyong Wu, Chao Yan, Chen Geng, Chen Wu, Cheng Yi, Chengli Feng, Chenglin Zhu, Chengting Feng, Chengyuan Yao, Daijiao Liu, DanNi Wan, Daxin Jiang, Dongjian Li, Dongqing Pang, Fei Tian, Feng Tian, Future Li, Gang Yu, Guanglong Yang, Haoyang Zhang, Hongyuan Wang, Jia Peng, Jiahao Song, Jialong Xue, Jiamin Fan, Jiangjie Zhen, Jianzheng Gao, Jincheng Wen, Jinghua Liang, Jinglan Gong, Jun Chen, Li Xie, Liang Zhao, Lifang Zhang, Lingli Ji, Lun Cai, Min Xu, Peilin Li, Peng Yang, Pengfei Tan, Qingjian Lin, Qinxin Du, Ruijie Xiong, Runze Li, Shenghua Hu, Shengqian Qin, Shi Qiu, Siqi Tu, Siyi Zhou, Tianjiao Deng, Wanying Lu, Weiming Niu, Wen Sun, WenWen Qu, Xiangyu Zhang, Xianwei Zhang, Xiaosu Su, Xing Chen, Xinyu Liu, Xuerui Yang, Yan Wu, Yang Li, Yang Yang, Yechang Huang, Yibo Zhu, Yifan Zhang, Yinuo Yan, Youjun Chen, Yu Fu, Yu Luo, Yu Zhou, Yujie Chen, Yumang Wang, Yunzhou Ju, Yuxiang Yang, Yuxin Li, Yuxin Zhang, Zekai Liu, Zengwei Yao, Zhaoxin Yuan, Zhenwei...
StepAudio 3 is a real-time voice model that listens, reasons, speaks, and uses tools concurrently for more natural spoken interaction.
Gilad D. Landau, Dulhan Jayalath, Oiwi Parker Jones
The work decodes what someone means from brain signals by translating MEG activity into semantic representations before generating text.
Sanyuan Chen, Min-Jae Hwang, Sho Inoue, Anna Sun, Bokai Yu, David Kant, Dongmin Hyun, Dorian Desblancs, Gregory Antonovsky, Oleg Repin, Peng-Jen Chen, Xutai Ma, Zehai Tu, Juan Pino, Wei-Ning Hsu
Text-AB is a large-scale speech generation system that turns text into expressive dubbed voices and natural two-way conversations without requiring explicit text-speech alignment.
Ziyang Ma, Zhikang Niu, Wenming Tu, Tianrui Wang, Ruiqi Yan, Junxi Liu, Yanru Huo, Nickk Huang, Yang Liu, Qicong Xie, Zeyu Xie, Hui Wang, Haitao Li, Zixuan Jiang, Yalin Li, Jie Fang, Yifan Duan, Zeyue Tian, Guangzheng Li, Haina Zhu, Shuyi Wang, Jinwen Wang, Mingyu Cui, Tian Tan, Auden, Sen Liang, Steve Yves, Shan Yang, Liefeng Bo, Zilong Zheng, Kai Yu, Eng-Siong Chng, Xie Chen
AuK is an open-source speech foundation model that can generate and edit audio from natural-language instructions, with a distilled version offering much faster inference.
Yiru Zhang, Hang Su, Lichun Fan, Ying Zeng, Chang Liu, Yifeng Wang, Yuquan Liang, Tao Li, Lian Li, Wenhao Yang, Jian Luan, Cong Zou, Heng Qu
Xiaomi-CocktailASR-1 uses a voice sample as a prompt to transcribe only the desired speaker in noisy conversations, while rejecting cases where that speaker is absent.
Francesco Mantegna, Dulhan Jayalath, Gereon Elvers, Tasha Kim, Benjamin Ballyk, Alex Fung, SungJun Cho, Teyun Kwon, Luisa Kurth, Miran Özdogan, Gilad Landau, Pratik Somaiya, Natalie Voets, Mark Woolrich, Oiwi Parker Jones
LibriBrain100 provides over 100 hours of standardized MEG speech data and benchmarks to accelerate noninvasive brain-to-text research.
Yujie Tu, Zhiliang Peng, Jianwei Yu, Li Dong, Songchen Xu, Yaoyao Chang, Wenhui Wang, Zilong Wang, Zehua Wang, Yan Xia, Jiajun Zhang, Xie Chen, Furu Wei
VibeVoice-ASR-Streaming enables an LLM to transcribe and identify speakers in real time, bringing unified speaker-aware speech recognition closer to voice-agent applications.
Zhifei Xie, Jiaqi Lang, Ze An, Yifan Zhao, Dongchao Yang, Kai Li, Ziyang Ma, Mingbao Lin, Chunyan Miao, Shuicheng Yan
VoiceMem gives real-time voice assistants separate factual and emotional memories so they can respond faster, more personally, and with greater empathy.
Kwan Yun, Serin Yoon, Sunjin Jung, Jung Eun Yoo, Inyup Lee, Junyong Noh
AnyTalk turns generic video-generation knowledge into real-time, lip-synced 3D animation for almost any character without requiring character-specific motion data.
Zhenghua Bao
Multi-hop RAG may retrieve more intelligently, but when speech recognition gets an entity wrong, that extra reasoning structure can make the final answer even worse.
Feiyu Shen, Kun Xie, Yichen Wu, Ziqi Dai, Yichen Han, Junjie Li, Xuelong Geng, Fenglong Xie, Lei Xie, Xu Tang, Yao Hu
FireRedTTS3 uses semantically enriched speech representations to make voice cloning, controllable speech generation, and audio editing more stable and capable.
Oluwanifemi Bamgbose, Simon Rosen, Jash Shah, Lindsay Devon Brin, Hoang H Nguyen, Anke Koelzer, Rachel Hansen, Tara Bogavelli, Fanny Riols
This paper tests whether automated TTS judges can recognize the specific linguistic flaws that humans hear, revealing that today’s evaluators often reduce speech quality to acoustics or depend heavily on prompting.
Feng Yin, Shuai Shi, Junjie Zheng, Kechenying Zhou, Yiqiu Wang, Chenyang He, Qiuhua Jiang, Mengxiao Bi, Yanmin Qian, Mingxin Chen, Xun Gong, Tianteng Gu, Bing Han, Peng Jiang, Chenda Li, Haiyang Sun, Han Wang, Wei Wang, Yi Wang, Leying Zhang, Wangyou Zhang, Chushu Zhou
Luna-TTS uses diffusion-style parallel speech generation to make expressive, multilingual text-to-speech faster, more controllable, and capable of voice cloning and editing.
Xingwei Sun, Heinrich Dinkel, Gang Li, Jiahao Mei, Yadong Niu, Zerui Han, Yuepeng Jiang, Jiahao Zhou, Lichun Fan, Jian Luan
MiDashengLM-Gen uses an LLM and flow matching to generate coherent multilingual audio scenes with speech, music, and sound effects while sharply improving speech intelligibility.
Yinhao Bai, Jinming Chen, Yafeng Chen, Wei Deng, Boya Dong, Nan Duan, Yu Gu, Weisheng Han, Yankun Huang, Ming Ke, Hao Li, Jingdong Li, Xiangyu Liang, Ning Liu, Yuan Liu, Ji Miao, Jiaqi Wang, Qi Wang, Wenchao Wang, Yuxuan Wang, Zhenfang Wang, Zhangyu Xiao, Chao Xue, Hongfei Xue, Fan Yu, Tianyi Zhang, Yuan Zhang, Yuqi Zhang, Lin Zhu
JoyAI-Talker is a full-duplex empathetic voice agent that combines language reasoning, expressive speech generation, and real-time interruption handling.
Yu Zhang, Ruiqi Li, Changhao Pan, Ke Lei, Xiang Yin, Cheng Yang
SwanTale aims to generate expressive multi-speaker dialogue and rich audio scenes from either natural-language instructions or a short voice reference.
Yuxiong Xu, Kaiqing Lin, Bin Li, Haodong Li, Sheng Li
ThinkOmni teaches an audio-capable language model to explain why a recording is fake and pinpoint exactly when the manipulation occurs.
Andrei Kuzmenko, Alexandr Maximenko, Aleksandr Kutsakov, Georgii Gospodinov, Dmitrii Bolotov, Oleg Kutuzov, Pavel Bogomolov, Fyodor Minkin
GigaAM Multilingual is a large speech foundation model and balancing recipe that improves ASR for data-poor Central Asian languages.
Aleksandr Kutsakov, Mariia Sadovina, Georgii Gospodinov, Alexandr Maximenko, Oleg Kutuzov, Pavel Bogomolov, Fyodor Minkin
GigaChat Audio teaches a large audio-language model to understand long recordings and answer questions with precise timestamps.
Laurin Wagner, Mario Zusag, Bernhard Thallinger
This work makes speech recognizers choose between clean and truly verbatim transcription while improving disfluency detection, word timing, and training-data creation.
Yexing Du, Kaiyuan Liu, Youcheng Pan, Bo Yang, Ming Liu, Bing Qin, Yang Xiang
This paper builds a privacy-preserving speech translation system that sends only compressed features from device to cloud, cutting bandwidth while scaling translation across 45 languages.
Bohan Li, Shi Lian, Hankun Wang, Yiwei Guo, Yu Xi, Zhihan Li, Da Zheng, Colin Zhang, Kai Yu
HoliTok is a new speech tokenization approach that compresses audio into a compact latent sequence usable for both speech generation and understanding, helping unify speech AI systems.
Yuyue Wang, Xihua Wang, Xin Cheng, Yijing Chen, Ruihua Song
This paper proposes a new way to generate combined speech and sound directly from natural language using an LLM-based planner and a new benchmark for composite audio.