XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs

Benchmark Model Rank Results
audio-compression-on-librispeech-test-clean-codec-reconstruction-low-bitrate-0-75-1-5-kbpsXY-Tokenizer#4PESQ-NB: 3.0SIM: 0.83STOI: 0.91PESQ-WB: 2.41