SRCodec: Split-residual vector quantization for neural speech codec

We present samples for SRCodec, our proposed framwork. Read our paper for more details.

We provide samples including four females and four males, randomly selected from our test set. We compare our proposed method with both traditional codecs and neural codecs, including Opus at 6 kbps and 9 kbps, Encodec at 3 kbps, Lyra-v1 at 3 kbps, and Lyra-v2 at 3.2 kbps, 6 kbps . The samples of Encodec are reported without Entropy Coding. All utterance signals are resampled to 16 kHz.

Thanks for your listening!

ID Methods Wav Ground truth
p225_331_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p225_350_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p225_356_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p226_030_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p226_044_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p233_183_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p233_189_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p262_368_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p262_392_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p362_017_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p362_063_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p362_113_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p364_215_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p364_220_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p374_004_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p374_051_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p374_071_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p376_007_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p376_014_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k
p376_036_mic2 SRCodec-0.95kbps
SRCodec-1.9kbps
SRCodec-3.8kbps
Encodec-3k
Lyra-v1
Opus-6k
Opus-9k
Speex-4k
Lyra-v2-3k
Lyra-v2-6k