论文解读
StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs
语音分词 | 9.0/10
量化
论文解读
AnyAccomp: Generalizable Accompaniment Generation Via Quantized Melodic Bottleneck
音乐生成 | 8.0/10
论文解读
S-PRESSO: Ultra Low Bitrate Sound Effect Compression with Diffusion Autoencoders and Offline Quantization
音频生成 | 7.5/10
论文解读
T-Mimi: A Transformer-Based Mimi Decoder for Real-Time On-Phone TTS
语音合成 | 7.0/10