作者ASLPer
作为语音相关研究领域的旗舰国际会议,INTERSPEECH2022(Annual Conference of the International Speech Communication Association)将于9月18-22日在韩国仁川举办,会议以线上和线下混合形式进行。会议官方网址为:https://interspeech2022.org。

#1
CaTT-KWS: A Multi-stage Customized Keyword Spotting Framework based on Cascaded Transducer-Transformer

(扫码看论文)
#2
Minimizing Sequential Confusion Error in Speech Command Recognition

(扫码看论文)
#3
Personalized Acoustic Echo Cancellation for Full-duplex Communications

(扫码看论文)
#4
Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASR

(扫码看论文)
#5
Improving Transformer-based Conversational ASR by Inter-Sentential Attention Mechanism

(扫码看论文)
#6
Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition

(扫码看论文)
#7
Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher

(扫码看论文)
#8
Learning Noise-independent Speech Representation for High-quality Voice Conversion for Noisy Target Speakers

(扫码看论文)
#9
A Comparative Study on Speaker-attributed Automatic Speech Recognition in Multi-party Meetings

(扫码看论文)
#10
Glow-WaveGAN 2: High-quality Zero-shot Text-to-speech Synthesis and Any-to-any Voice Conversion

(扫码看论文)
#11
Backend Ensemble for Speaker Verification and Spoofing Countermeasure

(扫码看论文)
#12
WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit

(扫码看论文)
相关文章
迷途小书僮,公众号:语音之家[开源代码]WeNet2.0:提高端到端ASR的生产力
#13
Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

(扫码看论文)
相关文章
朱鹏程,公众号:语音之家全球首个中文精标歌声合成开源数据Opencpop正式发布
#14
Cross-speaker Emotion Transfer Based on Prosody Compensation for End-to-End Speech Synthesis

(扫码看论文)
后续会对每篇论文进行解读分享,敬请关注。
